@fugood/buttress-server 2.24.5 → 2.24.6

package/README.md

@@ -100,48 +100,267 @@ The token claims `{ k: 'ba', w_id, st: 'ws', sid, jti, exp }` and any buttress-s
 
 ## Configuration
 
-Configuration can be provided via:
-- `--config` / `-c` flag with TOML file path
+Configuration is loaded from a TOML file passed via `--config` / `-c`. Every top-level table is optional — missing sections fall back to defaults. See `config/sample.toml` for an end-to-end example.
 
-### Configuration Format (TOML)
+### Top-level sections
+
+| Section                   | Purpose                                                                                            |
+| ------------------------- | -------------------------------------------------------------------------------------------------- |
+| `[env]`                   | Environment variables exported into the process **only if not already set**                        |
+| `[server]`                | HTTP/RPC listener (port, log level, body limits)                                                   |
+| `[runtime]`               | Global defaults shared by every generator (most `[generators.model]` keys may live here too)       |
+| `[runtime.session_cache]` | KV-cache reuse store — see [Session State Cache](#session-state-cache)                             |
+| `[autodiscover]`          | LAN UDP / HTTP / mDNS discovery toggles                                                            |
+| `[openai_compat]`         | Enable `/oai-compat/v1/*` — see [Compatibility Endpoints](#compatibility-endpoints-experimental)   |
+| `[anthropic_messages]`    | Enable `/anthropic-messages` — see [Compatibility Endpoints](#compatibility-endpoints-experimental)|
+| `[[generators]]`          | Array of generator instances — one entry per loaded model                                          |
+
+### `[env]`
 
 ```toml
-# Environment variables (only set if not already defined in system)
 [env]
-HF_TOKEN = "your_huggingface_token_here"
+HUGGINGFACE_TOKEN = "hf_xxx"   # ggml backends read this; HF_TOKEN is not picked up automatically
 CUDA_VISIBLE_DEVICES = "0"
+```
+
+Values here are exported only when the variable isn't already set in the process — see [Environment Variable Priority](#environment-variable-priority). For HuggingFace auth across all backends, `[runtime] huggingface_token = "hf_xxx"` works regardless of variable name.
+
+### `[server]`
+
+| Key               | Type           | Default                                                                |
+| ----------------- | -------------- | ---------------------------------------------------------------------- |
+| `id`              | string         | `buttress-<machineId>` — stable id used for autodiscover / binding     |
+| `name`            | string         | `Buttress Server (<short id>)` — display name                          |
+| `port`            | number         | `2080` (overridden by `--port`)                                        |
+| `log_level`       | `"debug"`/`"info"`/`"warn"`/`"error"` | unset                                          |
+| `max_body_size`   | string\|number | `"50MB"` — e.g. `"100MB"`, `"1GB"`, or raw bytes                       |
+| `session_timeout` | string\|number | `60000` ms — accepts ms numbers or duration strings (`"30s"`)          |
+| `temp_file_dir`   | string         | `$TMPDIR/.buttress`                                                    |
+
+### `[runtime]` — global generator defaults
+
+Most ggml-llm `[generators.model]` keys can also live in `[runtime]` as defaults. Per-generator values win; otherwise the runtime default applies.
+
+| Key                          | Type                          | Notes                                                                  |
+| ---------------------------- | ----------------------------- | ---------------------------------------------------------------------- |
+| `cache_dir`                  | string                        | Model + metadata cache root (default `~/.buttress/models`)             |
+| `huggingface_token`          | string                        | Falls back to `$HUGGINGFACE_TOKEN`                                     |
+| `http_headers`               | table                         | Extra headers attached to HF / HTTP downloads                          |
+| `context_release_delay_ms`   | number                        | Idle time before unloading a context (default `10000`; `0` = immediate)|
+| `prefer_variants`            | string[]                      | Override variant probe order (ggml backends)                           |
+| `n_threads`                  | number                        | CPU thread count                                                       |
+| `n_ctx`                      | number                        | Context window (per-model value wins; auto-capped at training context) |
+| `n_gpu_layers`               | number\|`"auto"`              | Layers offloaded to GPU (default `"auto"`)                             |
+| `n_batch` / `n_ubatch`       | number                        | Prompt batch / micro-batch size. **Note:** `n_batch` has a model-level default of `512` that shadows the runtime value unless `[generators.model] n_batch` is set explicitly. |
+| `n_parallel`                 | number                        | Parallel sequences (default `4`)                                       |
+| `n_cpu_moe`                  | number                        | MoE expert layers offloaded to CPU                                     |
+| `flash_attn_type`            | `"on"` / `"off"` / `"auto"`   | When a GPU backend is selected, defaults to `"auto"`; on CPU, defaults to `"off"`. Explicit `"on"` / `"off"` / `"auto"` overrides. |
+| `cache_type_k`, `cache_type_v` | string                      | KV-cache dtype (`f16`, `f32`, `q8_0`, `q4_0`, …)                       |
+| `kv_unified`                 | boolean                       | Use a unified KV cache across sequences                                |
+| `swa_full`                   | boolean                       | Materialize full attention even for sliding-window layers              |
+| `ctx_shift`                  | boolean                       | Allow llama.cpp's rolling context shift                                |
+| `use_mmap`, `use_mlock`      | boolean                       | Memory-mapping / locking                                               |
+| `no_extra_bufts`             | boolean                       | Disable extra compute buffer types                                     |
+| `cpu_mask`, `cpu_strict`     | string / boolean              | CPU affinity (advanced)                                                |
+| `devices`                    | string[]                      | Restrict to specific GGML devices                                      |
+| Speculative keys             | various                       | `speculative`, `spec_type`, `spec_draft_n_max/n_min/p_min/p_split`     |
+
+### `[autodiscover]`
+
+Set `autodiscover = true` for defaults, `false` (or omit) to disable, or a table for fine control:
 
-[server]
-port = 2080
-log_level = "info"
+```toml
+[autodiscover]
+udp.port = 8089
+udp.announcements = { enabled = true, interval = 5000 }
+udp.requests       = { enabled = true, responseDelay = 100 }
+http.enabled = true
+http.path    = "/buttress/info"
+http.cors    = true
+# mdns.enabled = false   # Bonjour/Avahi advertisement (optional)
+```
 
-[runtime]
-cache_dir = "~/.buttress/models"
+### `[[generators]]`
 
-# Session state cache for ggml-llm (saves KV cache to disk for prompt reuse)
-[runtime.session_cache]
-enabled = true
-max_size_bytes = "10GB"  # Supports string (e.g., "10GB", "500MB") or number
-max_entries = 1000
+Every generator entry has a `type`, an optional `[generators.backend]` table, and a `[generators.model]` table:
 
-# GGML LLM generator
+```toml
+[[generators]]
+type = "ggml-llm"        # or "ggml-stt" / "mlx-llm"
+
+[generators.backend]
+# (see per-type sections below)
+
+[generators.model]
+repo_id = "..."
+# (see per-type sections below)
+```
+
+#### Common `[generators.model]` keys
+
+Shared by **all** generator types:
+
+| Key                       | Type      | Notes                                                                            |
+| ------------------------- | --------- | -------------------------------------------------------------------------------- |
+| `repo_id` *(required)*    | string    | HuggingFace repo (`org/repo`)                                                    |
+| `revision`                | string    | Default `"main"`                                                                 |
+| `download`                | boolean   | Pre-download at server startup (default `false`)                                 |
+
+Additional keys honored by **ggml-llm** and **ggml-stt** (mlx-llm gets quantization from the repo itself and does not use these):
+
+| Key                       | Type      | Notes                                                                            |
+| ------------------------- | --------- | -------------------------------------------------------------------------------- |
+| `filename`                | string    | Pin a specific artifact in the repo                                              |
+| `url`                     | string    | Direct download URL (skips manifest lookup)                                      |
+| `quantization`            | string    | Preferred quant tag — e.g. `q4_0`, `q8_0`, `mxfp4`                               |
+| `preferred_quantizations` | string[]  | Ordered fallback list when `quantization` doesn't match (alias: `quantizations`) |
+| `allow_local_file`        | boolean   | Required to use `local_path` / `mmproj_local_path`                               |
+| `local_path`              | string    | Use a local file as the load path. Repo metadata is still resolved from HF, so `repo_id` is still required. |
+| `api_base`, `base_url`    | string    | Override HF API / blob hosts (mirrors / proxies)                                 |
+
+---
+
+### `ggml-llm` (llama.cpp via `@fugood/llama.node`)
+
+Loads a GGUF LLM. Runtime keys above can be overridden per-generator under `[generators.model]`; `[generators.backend]` only controls backend selection and resource planning.
+
+**`[generators.backend]`**
+
+| Key                   | Type     | Default                                       | Notes                                                            |
+| --------------------- | -------- | --------------------------------------------- | ---------------------------------------------------------------- |
+| `variant`             | string   | auto                                          | Force `cuda` / `vulkan` / `snapdragon` / `default`               |
+| `variant_preference`  | string[] | `["cuda","vulkan","snapdragon","default"]`    | Probe order when `variant` is unset                              |
+| `gpu_memory_fraction` | number   | `0.85`                                        | Max GPU fraction the hardware guardrails may plan against        |
+| `cpu_memory_fraction` | number   | `0.5`                                         | Max RAM fraction for CPU-side buffers                            |
+
+**`[generators.model]`** — in addition to the common keys above:
+
+| Key                                                                           | Type             | Notes                                                                |
+| ----------------------------------------------------------------------------- | ---------------- | -------------------------------------------------------------------- |
+| `n_ctx`                                                                       | number           | Context window. Auto-capped at the model's training context.         |
+| `n_gpu_layers`                                                                | number\|`"auto"` | Layers offloaded to GPU (default `"auto"`)                           |
+| `n_batch`                                                                     | number           | Prompt batch size (default `512`)                                    |
+| `n_ubatch`, `n_threads`, `n_parallel`, `n_cpu_moe`                            | number           | Same semantics as the `[runtime]` defaults                           |
+| `flash_attn_type`, `cache_type_k`, `cache_type_v`, `kv_unified`, `swa_full`, `ctx_shift`, `use_mmap`, `use_mlock`, `no_extra_bufts`, `cpu_mask`, `cpu_strict`, `devices` | various | Per-model overrides for the `[runtime]` defaults |
+
+**Multimodal (mtmd)** — auto-downloads the matching `mmproj-*.gguf` from the same repo and calls `initMultimodal`:
+
+| Key                       | Type    | Notes                                                              |
+| ------------------------- | ------- | ------------------------------------------------------------------ |
+| `enable_mtmd`             | boolean | Default `false`                                                    |
+| `mmproj_filename`         | string  | Pin a specific projector file                                      |
+| `mmproj_url`              | string  | Direct URL override                                                |
+| `mmproj_local_path`       | string  | Local projector (requires `allow_local_file = true`)               |
+| `mmproj_use_gpu`          | boolean | `null` = auto (true when `n_gpu_layers > 0`)                       |
+| `mmproj_image_min_tokens` | number  | Min visual tokens (dynamic-resolution models; `-1` = unset)        |
+| `mmproj_image_max_tokens` | number  | Max visual tokens (`-1` = unset)                                   |
+
+**Speculative decoding**
+
+| Key                  | Type   | Notes                                              |
+| -------------------- | ------ | -------------------------------------------------- |
+| `speculative`        | string | Draft model identifier                             |
+| `spec_type`          | string | Strategy (backend-defined)                         |
+| `spec_draft_n_max`   | int    | Max drafted tokens per step                        |
+| `spec_draft_n_min`   | int    | Min drafted tokens                                 |
+| `spec_draft_p_min`   | number | Min acceptance probability                         |
+| `spec_draft_p_split` | number | Split threshold                                    |
+
+**Example**
+
+```toml
 [[generators]]
 type = "ggml-llm"
 [generators.backend]
 variant_preference = ["cuda", "vulkan", "default"]
+gpu_memory_fraction = 0.95
 [generators.model]
 repo_id = "ggml-org/gpt-oss-20b-GGUF"
 quantization = "mxfp4"
 n_ctx = 12800
+download = true
+```
+
+---
+
+### `ggml-stt` (whisper.cpp via `@fugood/whisper.node`)
+
+Loads a Whisper GGML model for speech-to-text.
+
+**`[generators.backend]`**
 
-# GGML STT (Speech-to-Text) generator
+| Key                   | Type     | Default                       | Notes                              |
+| --------------------- | -------- | ----------------------------- | ---------------------------------- |
+| `variant`             | string   | auto                          | `cuda` / `vulkan` / `default`      |
+| `variant_preference`  | string[] | `["cuda","vulkan","default"]` | Probe order                        |
+| `gpu_memory_fraction` | number   | `0.85`                        |                                    |
+| `cpu_memory_fraction` | number   | `0.5`                         |                                    |
+
+**`[generators.model]`** — common keys plus:
+
+| Key                       | Type                          | Default                          | Notes                                                |
+| ------------------------- | ----------------------------- | -------------------------------- | ---------------------------------------------------- |
+| `repo_id`                 | string                        | `"BricksDisplay/whisper-ggml"`   | Defaulted (unlike ggml-llm)                          |
+| `preferred_quantizations` | string[]                      | `["q8_0", <no-quant>, "q5_1"]`   | Default fallback chain                               |
+| `use_gpu`                 | boolean                       | `true`                           | Force-disable GPU even when available                |
+| `use_flash_attn`          | `"on"` / `"off"` / `"auto"` / boolean | `"auto"`                 | `"auto"` enables flash-attn when GPU is in use. `true`/`false` are accepted as shortcuts for `"on"`/`"off"`. |
+
+**Runtime extras** — under `[runtime]` for ggml-stt only:
+
+| Key           | Type   | Notes                                       |
+| ------------- | ------ | ------------------------------------------- |
+| `max_threads` | number | Caps the whisper.cpp thread count           |
+
+**Example**
+
+```toml
 [[generators]]
 type = "ggml-stt"
 [generators.backend]
-variant_preference = ["coreml", "default"]
+variant_preference = ["cuda", "vulkan", "default"]
 [generators.model]
 repo_id = "BricksDisplay/whisper-ggml"
-filename = "ggml-small.bin"
+filename = "ggml-large-v3-turbo-q8_0.bin"
+use_gpu = true
+use_flash_attn = "on"
+download = true
+```
+
+---
+
+### `mlx-llm` (Apple Silicon, Python `mlx-lm` / `mlx-vlm` bridge)
+
+Loads an MLX-format model on Apple Silicon. On first use, the backend creates a virtualenv at `{cache_dir}/mlx-env` and installs `mlx_lm_package`, `mlx_vlm_package`, plus `torch` and `torchvision` (required by some VLM processors). If an existing venv already has `mlx_vlm` and `torch` importable, the install step is skipped. There is no `[generators.backend]` section.
+
+**`[generators.model]`** — common `repo_id` / `revision` / `download` plus:
+
+| Key                | Type                | Default   | Notes                                                                         |
+| ------------------ | ------------------- | --------- | ----------------------------------------------------------------------------- |
+| `adapter_path`     | string              | —         | Local LoRA adapter directory                                                  |
+| `vlm`              | `"auto"` / boolean  | `"auto"`  | Force VLM (`true`) vs text-only (`false`); `"auto"` infers from the repo      |
+| `tokenizer_config` | table               | —         | Forwarded to `mlx_lm.load(..., tokenizer_config=...)`                         |
+| `model_config`     | table               | —         | Forwarded to `mlx_lm.load(..., model_config=...)`                             |
+
+`quantization`, `filename`, and `preferred_quantizations` are **not** used — the MLX repo itself determines the quantization.
+
+**Runtime extras** — under `[runtime]` for mlx-llm:
+
+| Key                 | Type   | Default                       | Notes                                                                |
+| ------------------- | ------ | ----------------------------- | -------------------------------------------------------------------- |
+| `mlx_env_dir`       | string | `{cache_dir}/mlx-env`         | Location of the auto-managed Python venv                             |
+| `mlx_lm_package`    | string | `"mlx-lm==0.31.1"`            | pip spec used when provisioning the venv                             |
+| `mlx_vlm_package`   | string | `"mlx-vlm==0.4.0"`            | pip spec used when provisioning the venv                             |
+| `session_cache.*`   | table  | enabled, `5GB`, 100 entries   | Separate cache from ggml-llm (lives in `{cache_dir}/mlx-session-cache`) |
+
+**Example**
+
+```toml
+[[generators]]
+type = "mlx-llm"
+[generators.model]
+repo_id = "mlx-community/Qwen2.5-VL-3B-Instruct-4bit"
+vlm = true
+download = true
 ```
 
 ### Programmatic Usage

package/lib/index.mjs

@@ -1,12 +1,12 @@
 #!/usr/bin/env node
-import{t as e}from"./chunk-C8PTHxhX.mjs";import{node as t}from"@elysiajs/node";import{Elysia as n,file as r,sse as i,t as a}from"elysia";import o,{createHash as s,randomUUID as c}from"node:crypto";import l from"node:path";import*as u from"node:stream/web";import{ReadableStream as d}from"node:stream/web";import f,{mkdir as p,open as m,readFile as h,readdir as g,rename as _,stat as v,unlink as y,writeFile as b}from"node:fs/promises";import x from"node:os";import{gguf as S}from"@huggingface/gguf";import{getBackendDevicesInfo as C,isLibVariantAvailable as w,loadModel as T}from"@fugood/llama.node";import E from"bytes";import{EventEmitter as D}from"node:events";import{initWhisper as ee}from"@fugood/whisper.node";import{fileURLToPath as te}from"node:url";import{execFile as ne,execSync as O,spawn as re}from"node:child_process";import k from"node:fs";import A from"@iarna/toml";import{ZodError as j,z as M}from"zod";import{importSPKI as N,jwtVerify as P}from"jose";import{cors as ie}from"@elysiajs/cors";import F from"node-machine-id";import I from"ms";import{Buffer as L}from"node:buffer";import R from"node:dgram";const z=1024**3,ae=(e,t,n)=>Math.min(Math.max(e,t),n),oe=e=>e?40:0,se=(e=0)=>e?ae(e/(12*z)*20,0,20):0,ce=(e=0)=>e?ae(e/(32*z)*10,0,10):0,le=e=>e?10:0,B=(e=`default`,t=null)=>{let n=String(e).toLowerCase();return n?n.includes(`cuda`)?20:n.includes(`vulkan`)?10:n.includes(`default`)?t===`darwin`||t===`ios`?15:5:0:0},ue=({platform:e,variant:t,hasGpu:n,gpuUsableBytes:r=0,cpuUsableBytes:i=0,ok:a=!0}={})=>{if(!a)return 0;let o=oe(n)+B(t,e)+se(r),s=ce(i),c=le(a);return Math.min(100,Math.round(o+s+c))},de=({platform:e,variant:t,hasGpu:n,gpuUsableBytes:r=0,cpuUsableBytes:i=0,ok:a=!0}={})=>({gpuPresence:oe(n),variant:B(t,e),gpuMemory:se(r),cpuMemory:ce(i),availability:le(a)}),fe=[`cuda`,`vulkan`,`snapdragon`,`default`],pe=.85,me=.5,he=e=>!e&&e!==0?[]:Array.isArray(e)?e.filter(e=>e!=null):[e],ge=e=>e&&String(e).trim().toLowerCase()||null,_e=({variant:e,preferVariants:t=[],variantPreference:n=[],defaultVariants:r=fe}={})=>{let i=[];e&&i.push(e),i.push(...he(t)),i.push(...he(n)),i.push(...r);let a=new Set;for(let e of i){let t=ge(e);t&&a.add(t)}return Array.from(a)},ve=(e={})=>{let t=String(e.type||e.deviceType||e.kind||``).toLowerCase();return!!(t.includes(`gpu`)||t.includes(`cuda`)||t.includes(`metal`)||t.includes(`vulkan`)||t.includes(`snapdragon`))},ye=e=>Array.isArray(e)?e.map(e=>({...e})):[],be=(e,t)=>e===`snapdragon`?t.filter(e=>e.deviceName!==`GPUOpenCL`):t,xe=({platform:e,totalMemoryInBytes:t,variant:n,devices:r,gpuMemoryFraction:i,cpuMemoryFraction:a,ok:o,error:s})=>{let c=ye(be(n,r)),l=c.some(ve),u=c.filter(e=>ve(e)&&Number.isFinite(Number(e.maxMemorySize))).reduce((e,t)=>e+t.maxMemorySize,0),d=t,f=l?Math.floor(u*i):0,p=d?Math.floor(d*a):0,m={platform:e,variant:n,hasGpu:l,gpuUsableBytes:f,cpuUsableBytes:p,ok:o};return{platform:e,ok:o,variant:n,hasGpu:l,devices:c,gpuTotalBytes:u,gpuUsableBytes:f,cpuTotalBytes:d,cpuUsableBytes:p,score:ue(m),breakdown:o?de(m):null,error:s,timestamp:new Date().toISOString()}},Se=({device:e,modelBytes:t=0,kvCacheBytes:n=0}={})=>{if(!e)return{totalRequiredBytes:t+n,fitsInGpu:!1,fitsInCpu:!1,limiting:`unknown-device`};let r=Math.max(0,Number(t)||0)+Math.max(0,Number(n)||0),i=e.hasGpu&&r>0&&r<=e.gpuUsableBytes,a=r>0&&r<=e.cpuUsableBytes,o=`ok`;return!i&&e.hasGpu&&(o=`gpu-memory`),a||(o=i?`cpu-memory`:`insufficient-memory`),{totalRequiredBytes:r,fitsInGpu:i,fitsInCpu:a,limiting:o}},Ce=async({platform:e,variant:t=null,preferVariants:n=[],variantPreference:r=[],gpuMemoryFraction:i=pe,cpuMemoryFraction:a=me,includeBreakdown:o=!1,totalMemoryInBytes:s,modelBytes:c=null,kvCacheBytes:l=null,limitedKvCacheBytes:u=null,dependencies:d={},defaultVariants:f=fe}={})=>{let{getBackendDevicesInfo:p,isLibVariantAvailable:m}=d;if(typeof p!=`function`||typeof m!=`function`)throw TypeError(`GGML capability detection requires getBackendDevicesInfo and isLibVariantAvailable functions`);let h=_e({variant:t,preferVariants:n,variantPreference:r,defaultVariants:f}),g=[];for(let t of h)try{if(!await m(t))throw Error(`Variant ${t} not available on this platform`);let n=await p(t);g.push(xe({platform:e,totalMemoryInBytes:s,variant:t,devices:n,gpuMemoryFraction:i,cpuMemoryFraction:a,ok:!0}))}catch(n){let r=n instanceof Error?n.message:String(n);g.push(xe({platform:e,totalMemoryInBytes:s,variant:t,devices:[],gpuMemoryFraction:i,cpuMemoryFraction:a,ok:!1,error:r}))}let _=g.filter(e=>e.ok)[0]||null,v={ok:!!_,selected:_?{..._,breakdown:o?_.breakdown:void 0}:null,attempts:g};if(!o&&v.selected&&delete v.selected.breakdown,!v||!c&&!l)return v;let y=e=>{if(!e)return e;let t=Se({device:e,modelBytes:c||0,kvCacheBytes:l||0}),n=null;return u!=null&&u!==l&&(n=Se({device:e,modelBytes:c||0,kvCacheBytes:u})),{...e,fit:t,...n&&{limitedFit:n}}};return v.selected=y(v.selected),v.attempts=Array.isArray(v.attempts)?v.attempts.map(y):v.attempts,v},we=`ggml-llm`,Te=[`cuda`,`vulkan`,`default`],Ee=async({platform:e,variant:t=null,preferVariants:n=[],variantPreference:r=[],gpuMemoryFraction:i=pe,cpuMemoryFraction:a=me,includeBreakdown:o=!1,totalMemoryInBytes:s,modelBytes:c=null,processingBytes:l=null,kvCacheBytes:u=null,dependencies:d={}}={})=>Ce({platform:e,variant:t,preferVariants:n,variantPreference:r&&r.length>0?r:Te,gpuMemoryFraction:i,cpuMemoryFraction:a,includeBreakdown:o,totalMemoryInBytes:s,modelBytes:c,kvCacheBytes:l??u,dependencies:d,defaultVariants:Te}),De=async({platform:e,arch:t=null,unifiedMemoryFraction:n=.85,includeBreakdown:r=!1,totalMemoryInBytes:i,modelBytes:a=null,kvCacheBytes:o=null,limitedKvCacheBytes:s=null}={})=>{let c=[];e!==`darwin`&&c.push(`MLX requires macOS`),t&&t!==`arm64`&&c.push(`MLX requires Apple Silicon (arm64)`);let l=c.length===0,u=l?Math.floor(i*n):0,d={platform:e,variant:`mlx`,hasGpu:l,gpuUsableBytes:u,cpuUsableBytes:u,ok:l},f=ue(d),p=l?de(d):null,m={platform:e,ok:l,variant:`mlx`,hasGpu:l,unifiedMemory:!0,devices:l?[{type:`metal`,deviceName:`Apple Silicon (Unified Memory)`,maxMemorySize:i}]:[],gpuTotalBytes:l?i:0,gpuUsableBytes:u,cpuTotalBytes:i,cpuUsableBytes:u,score:f,breakdown:r?p:void 0,error:l?void 0:c.join(`; `),timestamp:new Date().toISOString()};r||delete m.breakdown;let h={ok:l,selected:l?m:null,attempts:[m],errors:l?[]:c};if(!a&&!o)return h;let g=e=>{if(!e)return e;let t=Se({device:e,modelBytes:a||0,kvCacheBytes:o||0}),n=null;return s!=null&&s!==o&&(n=Se({device:e,modelBytes:a||0,kvCacheBytes:s})),{...e,fit:t,...n&&{limitedFit:n}}};return h.selected=g(h.selected),h.attempts=h.attempts.map(g),h},Oe=new Map([[we,Ce],[`ggml-stt`,Ee],[`mlx-llm`,De]]),ke=async({platform:e,totalMemoryInBytes:t,backend:n=we,dependencies:r,...i}={})=>{let a=Oe.get(n);if(!a)throw Error(`No capability detector registered for backend "${n}"`);return await a({...i,dependencies:r,totalMemoryInBytes:t,platform:e})},Ae={f16:2,f32:4,q8_0:1,q6_k:.75,q5_k:.625,q5_k_m:.625,q5_k_s:.625,q5_1:.625,q5_0:.625,q4_k:.5,q4_k_m:.5,q4_k_s:.5,q4_1:.5,q4_0:.5,iq4_nl:.5},je=e=>Ae[e?String(e).toLowerCase():`f16`]||Ae.f16,Me=(e,t,n,r,i,a={},{totalLayers:o=null,swaLayers:s=0,swaContext:c=null,swaContextMultiplier:l=1,swaAdditionalTokens:u=0,swaFull:d=!1}={})=>{if(!e||!t||!n||!r||!i)return 0;let f=o!=null&&o!==void 0?Number(o):Number(e),p=Math.max(0,Math.floor(f));if(!p)return 0;let m=je(a.k),h=je(a.v),g=Number(n)*(Number(r)*m+Number(i)*h);if(!g)return 0;let _=Math.max(0,Number(t)||0),v=Math.min(p,Math.max(0,Math.floor(Number(s)||0))),y=Math.max(0,p-v),b=c!=null&&Number.isFinite(Number(c))?Math.max(0,Number(c)):_,x=Math.max(1,Number(l)||1),S=Math.max(0,Number(u)||0),C=b*x+S,w=d?_:Math.min(_,C),T=y*_+v*Math.max(0,Math.floor(w));return Math.round(g*T)},Ne=({modelBytes:e=0,audioLengthSeconds:t=30,sampleRate:n=16e3,bytesPerSample:r=4}={})=>{let i=Math.max(0,Number(e)||0),a=Math.max(0,Math.floor(Math.max(0,t)*n*r)),o=1024*1024,s=1024*o,c;c=i<200*o?120*o:i<500*o?140*o:i<2*s?150*o:160*o;let l;l=i<200*o?70*o:i<500*o?135*o:(2*s,220*o);let u;u=i<100*o?20*o:i<200*o?30*o:i<500*o?85*o:i<2*s?215*o:360*o;let d=c+l+u;return{modelBytes:i,audioBufferBytes:a,processingBufferBytes:d,totalBytes:i+d+a}},Pe=e=>e?String(e).trim().toLowerCase():null,Fe=(e={},t=null)=>{if(!e)return null;let n=Pe(t),r=n?`${n}.attention.sliding_window`:null,i=(r&&e[r]!=null?e[r]:null)??e[`llama.attention.sliding_window`];if(i==null)return null;let a=Number(i);return Number.isFinite(a)?a:null},Ie=(e=0,t=0,n=!1)=>{let r=Math.max(0,Math.floor(Number(e)||0)),i=Math.max(0,Math.floor(Number(t)||0));if(!r||i===1)return 0;if(i<=0)return r;let a=Math.max(0,i-1),o=Math.floor(r/i),s=r%i,c=n?Math.max(0,s-1):Math.min(s,a);return o*a+c},Le=({arch:e,nLayer:t=0})=>({arch:Pe(e),enabled:!1,window:null,pattern:null,denseFirst:!1,type:null,kvLayers:Math.max(0,Math.floor(Number(t)||0)),swaLayers:0}),Re=new Map([[`llama4`,({nSwa:e})=>e===0?{enabled:!1}:{enabled:!0,window:e&&e>0?e:8192,pattern:4,type:`chunked`}],[`afmoe`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`phi3`,()=>({enabled:!1})],[`gemma2`,({nSwa:e})=>{let t=e&&e>0?e:4096;return t?{enabled:!0,window:t,pattern:2,type:`standard`}:{enabled:!1}}],[`gemma3`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:6,type:`standard`}],[`gemma3n`,({nLayer:e,nSwa:t})=>!t||t<=0?{enabled:!1}:{enabled:!0,window:t,pattern:5,type:`standard`,kvLayers:Math.min(20,e)}],[`gemma-embedding`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:6,type:`symmetric`}],[`cohere2`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`olmo2`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`exaone4`,({nLayer:e,nSwa:t})=>{let n=e>=64,r=null;return t&&t>0?r=t:n&&(r=4096),r?{enabled:!0,window:r,pattern:4,type:`standard`}:{enabled:!1}}],[`gpt-oss`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:2,type:`standard`}],[`gemma4`,({nLayer:e,nSwa:t,metadata:n})=>{if(!t||t<=0)return{enabled:!1};let r=Number(n?.[`gemma4.attention.shared_kv_layers`])||0,i=Math.max(0,e-r),a=n?.[`gemma4.attention.sliding_window_pattern`];return Array.isArray(a)?{enabled:!0,window:t,type:`standard`,swaLayers:a.slice(0,i).filter(e=>Number(e)>0).length,kvLayers:i}:{enabled:!0,window:t,pattern:6,type:`standard`,kvLayers:i}}],[`smallthinker`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:4096,pattern:4,denseFirst:!0,type:`standard`}]]),ze=({arch:e,metadata:t={},nLayer:n=0}={})=>{let r=Pe(e||t[`general.architecture`]),i=Math.max(0,Math.floor(Number(n)||0)),a=Fe(t,r),o=r?Re.get(r):null;if(!o)return Le({arch:r,nLayer:n});let s=o({nLayer:i,nSwa:a,metadata:t});if(!s||!s.enabled||!s.window||s.window<=0)return Le({arch:r,nLayer:n});let c=Math.max(0,Math.floor(Number(s.pattern)||0)),l=s.kvLayers!=null&&Number.isFinite(Number(s.kvLayers))?Number(s.kvLayers):i,u=Math.max(0,Math.floor(l)),d=s.swaLayers!=null&&Number.isFinite(Number(s.swaLayers))?Math.max(0,Math.floor(Number(s.swaLayers))):Ie(u,c,!!s.denseFirst);return{arch:r,enabled:d>0,window:s.window,pattern:c,denseFirst:!!s.denseFirst,type:s.type||`standard`,kvLayers:u,swaLayers:d}},Be=new Set([`mamba`,`mamba2`,`rwkv6`,`rwkv6qwen2`,`rwkv7`,`arwkv7`]),Ve=new Set([`jamba`,`falcon-h1`,`plamo2`,`granitehybrid`,`lfm2`,`lfm2moe`,`nemotron_h`,`nemotron_h_moe`,`qwen3next`]),He=e=>e?String(e).trim().toLowerCase():null,Ue=e=>{let t=He(e);return t?Be.has(t):!1},We=e=>{let t=He(e);return t?Ve.has(t):!1},Ge=e=>Ue(e)?`recurrent`:We(e)?`hybrid`:`transformer`,Ke=(e={})=>{let t=e[`general.architecture`],n=(t,n=null)=>{let r=e[t],i=Number(r);return Number.isFinite(i)?i:n},r=(t,n=null)=>{let r=e[t];if(Array.isArray(r))return r;let i=Number(r);return Number.isFinite(i)?i:n},i=t?n(`${t}.context_length`,n(`llama.context_length`)):null,a=t?n(`${t}.block_count`,n(`llama.block_count`)):null,o=t?n(`${t}.embedding_length`,n(`llama.embedding_length`)):null,s=t?n(`${t}.attention.head_count`,n(`llama.attention.head_count`)):null,c=t?r(`${t}.attention.head_count_kv`,r(`llama.attention.head_count_kv`,s)):null,l=null,u=null;if(Array.isArray(c)){let e=c.filter(e=>Number(e)>0);e.length>0?(l=Math.max(...e.map(Number)),u=e.length):(l=0,u=0)}else l=c;let d=t?n(`${t}.attention.key_length`,n(`llama.attention.key_length`)):null,f=t?n(`${t}.attention.value_length`,n(`llama.attention.value_length`)):null,p=e[`general.quantization_version`]||null,m=e[`general.file_type`]||null,h=t?n(`${t}.ssm.conv_kernel`):null,g=t?n(`${t}.ssm.state_size`):null,_=t?n(`${t}.ssm.inner_size`):null,v=t?n(`${t}.ssm.group_count`):null,y=t?n(`${t}.ssm.time_step_rank`):null,b=t?n(`${t}.rwkv.head_size`):null,x=t?n(`${t}.rwkv.token_shift_count`,2):null,S=t?n(`${t}.attention.shared_kv_layers`,0):0,C=u!=null&&a!=null?a-u:null;return{arch:t,nCtxTrain:i,nLayer:a,nEmbd:o,nHead:s,nHeadKv:l,nEmbdHeadK:d,nEmbdHeadV:f,quantVersion:p,fileType:m,attentionLayerCount:u,recurrentLayerCount:C,ssmDConv:h,ssmDState:g,ssmDInner:_,ssmNGroup:v,ssmDtRank:y,rwkvHeadSize:b,rwkvTokenShiftCount:x,sharedKvLayers:S}},qe=({layerCount:e,headKvCount:t,embdHeadKCount:n,embdHeadVCount:r,cacheTypes:i,swaConfig:a,kvUnified:o=!1,nParallel:s=1,swaFull:c=!1,arch:l=null,attentionLayerCount:u=null})=>{let d=Ge(l);if(d===`recurrent`)return()=>0;let f=d===`hybrid`&&u!=null?Math.max(0,Math.floor(Number(u)||0)):e,p=a?.window&&o?Math.max(1,Number(s)||1):1,m=o?1:Math.max(1,Number(s)||1);return e=>Me(f,e,t,n,r,i,{totalLayers:f,swaLayers:a?.swaLayers||0,swaContext:a?.window,swaFull:c,swaContextMultiplier:p})*m},Je=({nLayer:e,nEmbd:t,recurrentLayerCount:n=null,nSeqMax:r=1,ssmDConv:i=null,ssmDState:a=null,ssmDInner:o=null,ssmNGroup:s=null,ssmDtRank:c=null,rwkvHeadSize:l=null,rwkvTokenShiftCount:u=2,arch:d=null})=>{if(Ge(d)===`transformer`)return 0;let f=n==null?Math.max(0,Math.floor(Number(e)||0)):Math.max(0,Math.floor(Number(n)||0));if(f===0)return 0;let p=Math.max(1,Math.floor(Number(r)||1)),m=0,h=0;if(l!=null&&l>0&&t!=null&&t>0)m=Math.max(1,Number(u)||2)*t,h=t*l;else if(a!=null&&o!=null){let e=Math.max(0,Number(i)||0),t=Math.max(0,Number(a)||0),n=Math.max(0,Number(o)||0),r=Math.max(1,Number(s)||1);Math.max(0,Number(c)||0)>0?(m=e>0?(e-1)*2*r*t:0,h=Math.floor(t*n/2)):(m=e>0?(e-1)*(n+2*r*t):0,h=t*n)}else return 0;let g=(m+h)*p*f*4;return Math.max(0,g)},Ye=({maxCtx:e,availableMemory:t,modelBytes:n,kvBytesForCtx:r})=>{let i=Math.max(1,Math.floor(Number(e)||0));if(!r||t<=n)return i;let a=1,o=i,s=i;for(;a<=o;){let e=Math.floor((a+o)/2);n+r(e)<=t?(s=e,a=e+1):o=e-1}return s},V=new D;V.setMaxListeners(100);const Xe=(e,t,n)=>{e.push({...t,timestamp:t.timestamp||new Date().toISOString()}),e.length>n&&e.shift()};var Ze=class{constructor(e=9999){this.maxEntries=e,this.modelLoads=[],this.completions=[],this.transcriptions=[]}addModelLoad(e){Xe(this.modelLoads,e,this.maxEntries),V.emit(`status:modelLoad`,e),V.emit(`status:change`,{type:`modelLoad`,entry:e})}addCompletion(e){Xe(this.completions,e,this.maxEntries),V.emit(`status:completion`,e),V.emit(`status:change`,{type:`completion`,entry:e})}addTranscription(e){Xe(this.transcriptions,e,this.maxEntries),V.emit(`status:transcription`,e),V.emit(`status:change`,{type:`transcription`,entry:e})}getModelLoadHistory(){return[...this.modelLoads].reverse()}getCompletionHistory(){return[...this.completions].reverse()}getTranscriptionHistory(){return[...this.transcriptions].reverse()}clear(){this.modelLoads=[],this.completions=[],this.transcriptions=[]}};const H=new Ze,U=new Ze;let Qe=0;function $e(e){let t=t=>e(t);return V.on(`status:change`,t),()=>V.off(`status:change`,t)}function et(e){return Qe+=1,{subscriberId:Qe,unsubscribe:$e(e)}}function tt(e){let t=[];return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`ggml-llm`).map(([e,n])=>{let{instance:r}=n,i=[];return r.contexts&&(i=Array.from(r.contexts.entries()).map(([n,r])=>{let i={key:n,refCount:r.refCount,hasModel:!!r.context},a=r.context.parallel.getStatus();return i.parallelStatus=a,t.push({generatorId:e,contextKey:n,...a}),i})),{id:e,type:n.type,refCount:n.refCount,repoId:r.info?.model?.repoId||null,quantization:r.info?.model?.quantization||null,variant:r.info?.runtime?.variant||null,nCtx:r.info?.runtime?.n_ctx||null,nParallel:r.info?.runtime?.n_parallel||null,contexts:i}}),parallelStatuses:t,history:{modelLoads:H.getModelLoadHistory().filter(e=>e.variant!==`mlx`),completions:H.getCompletionHistory().filter(e=>e.variant!==`mlx`)}}}function nt(e){return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`ggml-stt`).map(([e,t])=>{let{instance:n}=t,r=n.getStatus?.()||{},i=r.queueStatus||{processing:!1,queuedCount:0};return{id:e,type:t.type,refCount:t.refCount,repoId:n.info?.model?.repoId||null,quantization:n.info?.model?.quantization||null,modelType:n.info?.model?.modelType||null,variant:n.info?.runtime?.variant||null,hasContext:r.hasContext||!1,contextRefCount:r.contextRefCount||0,queueStatus:i}}),history:{modelLoads:U.getModelLoadHistory(),transcriptions:U.getTranscriptionHistory()}}}function rt(e){return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`mlx-llm`).map(([e,t])=>{let{instance:n}=t,r=n.getStatus?.()||{};return{id:e,type:t.type,refCount:t.refCount,repoId:r.repoId||n.info?.model?.repoId||null,variant:r.variant||`mlx`,contexts:r.contexts||[]}}),history:{modelLoads:H.getModelLoadHistory().filter(e=>e.variant===`mlx`),completions:H.getCompletionHistory().filter(e=>e.variant===`mlx`)}}}function it(e){return{timestamp:new Date().toISOString(),ggmlLlm:tt(e),ggmlStt:nt(e),mlxLlm:rt(e)}}const{ReadableStream:at,WritableStream:ot}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,st=(e,t)=>Object.prototype.hasOwnProperty.call(e||{},t),ct=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),ct(e[t],n)):e[t]=n}),e),lt=`https://huggingface.co`,ut=`https://huggingface.co/api`,W=l.join(x.homedir(),`.buttress`,`models`),dt=[`mxfp4`,`q8_0`,`q6_k`,`q6`,`q5_k_m`,`q5_k_s`,`q5_k`,`q5_1`,`q5_0`,`q4_k_m`,`q4_k_s`,`q4_k`,`q4_1`,`q4_0`,`q3`,`q2`],ft=.5,pt=[`speculative`,`spec_type`,`spec_draft_n_max`,`spec_draft_n_min`,`spec_draft_p_min`,`spec_draft_p_split`],mt=(e,t)=>{if(!(t==null||t===``)){if(e===`spec_draft_n_max`||e===`spec_draft_n_min`){let e=Number(t);return Number.isFinite(e)?Math.max(0,Math.floor(e)):void 0}if(e===`spec_draft_p_min`||e===`spec_draft_p_split`){let e=Number(t);return Number.isFinite(e)?Math.max(0,e):void 0}return t}},ht=e=>{let t={};for(let n of pt){let r=mt(n,e.model[n]??e.runtime[n]);r!==void 0&&(t[n]=r)}return t},gt=(e={})=>{let t={};for(let n of pt){let r=mt(n,e[n]);r!==void 0&&(t[n]=r)}return t},_t=(e={},t={})=>{let n=e||{},r=gt(t);return!Object.keys(r).length||pt.some(e=>st(n,e))?n:{...r,...n}},vt={backend:{type:`ggml-llm`,variant:null,variant_preference:[`cuda`,`vulkan`,`snapdragon`,`default`],gpu_memory_fraction:.85,cpu_memory_fraction:ft},model:{repo_id:null,revision:`main`,filename:null,url:null,quantization:null,preferred_quantizations:[],n_ctx:null,n_gpu_layers:`auto`,allow_local_file:!1,local_path:null,api_base:ut,base_url:lt,enable_mtmd:!1,mmproj_filename:null,mmproj_url:null,mmproj_local_path:null,mmproj_use_gpu:null,mmproj_image_min_tokens:-1,mmproj_image_max_tokens:-1,speculative:null,spec_type:null,spec_draft_n_max:null,spec_draft_n_min:null,spec_draft_p_min:null,spec_draft_p_split:null},runtime:{cache_dir:W,prefer_variants:[],huggingface_token:process.env.HUGGINGFACE_TOKEN||null,http_headers:{},session_cache:{enabled:!0,max_size_bytes:10*1024*1024*1024,max_entries:1e3},context_release_delay_ms:1e4}},yt=(e,t=[])=>!e&&e!==0?[...t]:Array.isArray(e)?e.filter(e=>e!=null):[e],bt=e=>{if(!e)return null;let t=String(e).toLowerCase();return[`cuda`,`vulkan`,`snapdragon`,`default`].includes(t)?t:null},xt=(e={})=>{let t=structuredClone(vt);if(ct(t,e),t.backend.variant=bt(t.backend.variant),t.backend.variant_preference=Array.from(new Set(yt(t.backend.variant_preference).flatMap(e=>{let t=bt(e);return t?[t]:[]}))),t.backend.variant_preference.length===0&&(t.backend.variant_preference=[`cuda`,`vulkan`,`snapdragon`,`default`]),t.runtime.prefer_variants=Array.from(new Set(yt(t.runtime.prefer_variants).flatMap(e=>{let t=bt(e);return t?[t]:[]}))),t.model.preferred_quantizations=Array.from(new Set(yt(t.model.preferred_quantizations||t.model.quantizations).map(e=>e?String(e).toLowerCase():null).filter(Boolean))),t.model.quantization){let e=String(t.model.quantization).toLowerCase();t.model.preferred_quantizations.includes(e)||t.model.preferred_quantizations.unshift(e)}t.model.n_parallel=t.model.n_parallel?Math.max(1,Number(t.model.n_parallel)):void 0,t.model.n_batch=Math.max(1,Number(t.model.n_batch)||512),t.model.base_url=t.model.base_url||lt,t.model.api_base=t.model.api_base||ut,t.model.enable_mtmd=!!t.model.enable_mtmd;let n=e=>{if(e==null)return-1;let t=Number(e);return Number.isFinite(t)?Math.floor(t):-1};return t.model.mmproj_image_min_tokens=n(t.model.mmproj_image_min_tokens),t.model.mmproj_image_max_tokens=n(t.model.mmproj_image_max_tokens),t.runtime.cache_dir=t.runtime.cache_dir?l.resolve(t.runtime.cache_dir):W,t.runtime.session_cache={...vt.runtime.session_cache,...t.runtime.session_cache||{}},t.runtime.context_release_delay_ms=Math.max(0,Number(t.runtime.context_release_delay_ms)||vt.runtime.context_release_delay_ms),t},St=e=>{let t=e.toLowerCase();return dt.find(e=>t.includes(e))||null},Ct=e=>{let t=[];return e.backend.variant&&t.push(e.backend.variant),e.runtime.prefer_variants.length>0&&t.push(...e.runtime.prefer_variants),t.push(...e.backend.variant_preference),t.push(`default`),Array.from(new Set(t.flatMap(e=>{let t=bt(e);return t?[t]:[]})))},G=async e=>{await p(e,{recursive:!0})},wt=(e=W)=>l.join(e,`.metadata-cache`),Tt=(e,t,n=W)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(wt(n),t,`${r}.json`)},Et=async(e,t,n=W)=>{try{let r=Tt(e,t,n),i=await h(r,`utf-8`);return console.log(`[Cache] Hit ${t} cache:`,l.basename(r)),JSON.parse(i,(e,t)=>typeof t==`string`&&t.startsWith(`__bigint__`)?BigInt(t.slice(10)):t)}catch{return null}},Dt=async(e,t,n,r=W)=>{try{let i=Tt(e,t,r);await G(l.dirname(i)),await b(i,JSON.stringify(n,(e,t)=>typeof t==`bigint`?`__bigint__${t.toString()}`:t),`utf-8`),console.log(`[Cache] Wrote ${t} cache:`,l.basename(i))}catch(e){console.warn(`[Cache] Failed to write ${t} cache:`,e.message)}},Ot=(e=W)=>l.join(e,`.session-state-cache`),kt=(e=W)=>l.join(Ot(e),`cache-map.json`),At=(e=W)=>l.join(Ot(e),`temp`),jt=(e=W)=>l.join(Ot(e),`states`),Mt=()=>({version:1,entries:{},totalSize:0}),Nt=async(e=W)=>{try{let t=await h(kt(e),`utf-8`),n=JSON.parse(t);return!n.entries||typeof n.entries!=`object`?Mt():n}catch{return Mt()}},Pt=async(e,t=W)=>{let n=kt(t),r=`${n}.tmp.${Date.now()}`;try{await G(l.dirname(n)),await b(r,JSON.stringify(e,null,2),`utf-8`),await _(r,n)}catch(e){throw await y(r).catch(()=>{}),e}},Ft=(e,t)=>{let n=JSON.stringify({text:e,model:t.modelPath,variant:t.variant,n_gpu_layers:t.n_gpu_layers,n_ctx:t.n_ctx,cacheTypeK:t.cacheTypeK,cacheTypeV:t.cacheTypeV,kvUnified:t.kvUnified,swaFull:t.swaFull,flashAttnType:t.flashAttnType});return s(`sha256`).update(n).digest(`hex`).slice(0,24)},It=(e,t=W)=>l.join(jt(t),`${e}.bin`),Lt=(e=W)=>{let t=`${Date.now()}-${Math.random().toString(36).slice(2,10)}`;return l.join(At(e),`${t}.bin`)},Rt=(e,t)=>e.modelPath===t.modelPath&&e.variant===t.variant&&e.n_gpu_layers===t.n_gpu_layers&&e.n_ctx>=t.n_ctx&&e.cacheTypeK===t.cacheTypeK&&e.cacheTypeV===t.cacheTypeV&&e.kvUnified===t.kvUnified&&e.swaFull===t.swaFull&&e.flashAttnType===t.flashAttnType&&!!e.isRecurrent==!!t.isRecurrent&&!!e.isHybrid==!!t.isHybrid,zt=(e,t)=>{let n=Math.min(e.length,t.length),r=0;for(;r<n&&e[r]===t[r];)r+=1;return r},Bt=(e,t,n,r=!1)=>{let i=Object.values(n.entries);console.log(`[SessionCache] Finding match for promptText (${e.length} chars), exactMatch=${r}`),console.log(`[SessionCache] Checking ${i.length} cache entries`);let a=i.filter(e=>Rt(e.metadata,t));if(r){let t=a.find(t=>t.fullText===e);return t?(console.log(`[SessionCache] Exact match found: ${t.id} (${t.fullText.length} chars)`),{entry:t,prefixLength:t.fullText.length,exactMatch:!0}):null}let o=a.reduce((t,n)=>{let r=zt(e,n.fullText);return r>t.prefixLen||r===t.prefixLen&&n.fullText.length>(t.entry?.fullText?.length||0)?{entry:n,prefixLen:r}:t},{entry:null,prefixLen:0});return o.entry?(console.log(`[SessionCache] Prefix match found: ${o.entry.id} (${o.prefixLen}/${o.entry.fullText.length} chars)`),{entry:o.entry,prefixLength:o.prefixLen}):(console.log(`[SessionCache] No match found`),null)},Vt=async(e,t,n)=>{let r=Object.values(e.entries),i=r.sort((e,t)=>new Date(e.lastAccessedAt)-new Date(t.lastAccessedAt)),a=e.totalSize,o=r.length,s=i.filter(e=>!(a>t)&&!(o>n)?!1:(a-=(e.stateFileSize||0)+(e.promptStateSize||0),--o,!0));return await Promise.all(s.map(async t=>{await y(t.stateFilePath).catch(()=>{}),t.promptStatePath&&await y(t.promptStatePath).catch(()=>{}),delete e.entries[t.id],console.log(`[SessionCache] Evicted entry: ${t.id}`)})),e.totalSize=Math.max(0,a),s.map(e=>e.id)},Ht=async(e,t,n,r)=>{let i=[];for(let[a,o]of Object.entries(e.entries))a!==n&&Rt(o.metadata,r)&&t.startsWith(o.fullText)&&o.fullText.length<t.length&&i.push(o);return await Promise.all(i.map(async t=>{await y(t.stateFilePath).catch(()=>{}),t.promptStatePath&&await y(t.promptStatePath).catch(()=>{}),e.totalSize-=(t.stateFileSize||0)+(t.promptStateSize||0),delete e.entries[t.id],console.log(`[SessionCache] Evicted superseded prefix entry: ${t.id} (${t.promptText.length} prompt chars)`)})),i.map(e=>e.id)},Ut=async(e=W)=>{let t=At(e);try{let e=await g(t),n=Date.now();await Promise.all(e.map(async e=>{let r=l.join(t,e),i=await v(r).catch(()=>null);i&&n-i.mtimeMs>36e5&&(await y(r).catch(()=>{}),console.log(`[SessionCache] Cleaned up temp file: ${e}`))}))}catch{}},Wt=async e=>{try{return await v(e),!0}catch{return!1}},Gt=(e,t)=>e==null?t:typeof e==`number`?e:typeof e==`string`?E.parse(e)??t:t;var Kt=class e{constructor(e,t){this.config=e,this.plan=t,this.baseDir=e.runtime.cache_dir,this.enabled=e.runtime.session_cache?.enabled!==!1,this.maxSizeBytes=Gt(e.runtime.session_cache?.max_size_bytes,10*1024*1024*1024),this.maxEntries=e.runtime.session_cache?.max_entries||1e3,this.metadata={variant:t.info?.runtime?.variant||null,n_gpu_layers:t.info?.runtime?.n_gpu_layers||0,n_ctx:t.info?.runtime?.n_ctx||0,modelPath:t.localPath,cacheTypeK:t.info?.runtime?.cache_type_k||`f16`,cacheTypeV:t.info?.runtime?.cache_type_v||`f16`,kvUnified:t.info?.runtime?.kv_unified??null,swaFull:t.info?.runtime?.swa_full??null,flashAttnType:t.info?.runtime?.flash_attn_type||`off`,isRecurrent:!1,isHybrid:!1},this.cacheMap=null,this.initialized=!1}updateModelInfo(e){e&&(this.metadata.isRecurrent=!!e.is_recurrent,this.metadata.isHybrid=!!e.is_hybrid,(this.metadata.isRecurrent||this.metadata.isHybrid)&&console.log(`[SessionCache] Model architecture: recurrent=${this.metadata.isRecurrent}, hybrid=${this.metadata.isHybrid}`))}requiresExactMatch(){return this.metadata.isRecurrent||this.metadata.isHybrid}async persistCacheMap(){try{await Pt(this.cacheMap,this.baseDir)}catch(e){console.warn(`[SessionCache] Failed to persist cache map: ${e?.message||e}`)}}static checkTokenPrefixMatch(e,t){if(e.length>t.length)return!1;for(let n=0;n<e.length;n+=1)if(e[n]!==t[n])return!1;return!0}static async tokenizeToArray(e,t){let n=await e.tokenize(t);return Array.from(n?.tokens||[])}async findFormattedMatchForRecurrent(t,n,r){let i=await e.tokenizeToArray(r,n),a=t.map(async t=>{try{let n=await e.tokenizeToArray(r,t.fullText);if(e.checkTokenPrefixMatch(n,i))return{entry:t,usePromptState:!1,tokenCount:n.length};if(t.promptStatePath&&t.promptText){let n=await e.tokenizeToArray(r,t.promptText);if(e.checkTokenPrefixMatch(n,i))return{entry:t,usePromptState:!0,tokenCount:n.length}}return null}catch(e){return console.warn(`[SessionCache] Failed to check entry ${t.id}: ${e.message}`),null}}),o=(await Promise.all(a)).find(e=>e!==null);if(!o)return console.log(`[SessionCache] No token prefix match found for recurrent/hybrid model`),null;let{entry:s,usePromptState:c,tokenCount:l}=o;return console.log(`[SessionCache] Token prefix match: ${s.id} (${l} tokens, usePromptState=${c})`),await Wt(c?s.promptStatePath:s.stateFilePath)?(s.lastAccessedAt=new Date().toISOString(),await this.persistCacheMap(),{entry:s,usePromptState:c}):(await this.removeStaleEntry(s),null)}async initialize(){if(!(!this.enabled||this.initialized))try{await G(Ot(this.baseDir)),await G(At(this.baseDir)),await G(jt(this.baseDir)),this.cacheMap=await Nt(this.baseDir),this.initialized=!0,console.log(`[SessionCache] Initialized with ${Object.keys(this.cacheMap.entries).length} entries`)}catch(e){console.warn(`[SessionCache] Failed to initialize: ${e.message}`),this.enabled=!1}}async removeStaleEntry(e){console.log(`[SessionCache] Removing stale entry: ${e.id}`),e.stateFilePath&&await y(e.stateFilePath).catch(()=>{}),e.promptStatePath&&await y(e.promptStatePath).catch(()=>{}),delete this.cacheMap.entries[e.id],this.cacheMap.totalSize-=(e.stateFileSize||0)+(e.promptStateSize||0),await this.persistCacheMap()}async findMatchingEntry(e,t=null){if(!this.enabled||!this.cacheMap)return null;let n=this.requiresExactMatch();if(n&&t){let n=Object.values(this.cacheMap.entries).filter(e=>Rt(e.metadata,this.metadata)&&e.fullText);return this.findFormattedMatchForRecurrent(n,e,t)}let r=Bt(e,this.metadata,this.cacheMap,n);if(!r)return null;let{entry:i}=r;return await Wt(i.stateFilePath)?(i.lastAccessedAt=new Date().toISOString(),await this.persistCacheMap(),{entry:i,usePromptState:!1}):(await this.removeStaleEntry(i),null)}async prepareCompletionOptions(e,t,n=null){let r={options:e,cacheEntry:null,promptPrefix:null};if(!this.enabled)return r;let i=await this.findMatchingEntry(t,n);if(!i)return r;let{entry:a,usePromptState:o}=i,s=o?a.promptStatePath:a.stateFilePath,c=o?a.promptText:a.fullText;return console.log(`[SessionCache] Found matching entry: ${a.id} (${c.length} chars, usePromptState=${o})`),{options:{...e,load_state_path:s},cacheEntry:a,promptPrefix:c}}async saveCompletionState(e,t,n,r=0,i=null){if(!this.enabled)return null;let a=e+t,o=Ft(a,this.metadata),s=()=>{n&&y(n).catch(()=>{}),i&&y(i).catch(()=>{})};if(this.cacheMap.entries[o]){console.log(`[SessionCache] Entry already exists for prompt: ${o}, updating position`);let e=this.cacheMap.entries[o];return e.lastAccessedAt=new Date().toISOString(),delete this.cacheMap.entries[o],this.cacheMap.entries[o]=e,await this.persistCacheMap(),s(),e}let c=It(o,this.baseDir),u=i?It(`${o}-prompt`,this.baseDir):null;try{await G(l.dirname(c)),await _(n,c);let s=await v(c),d=0;if(i&&u)try{await _(i,u),d=(await v(u)).size,console.log(`[SessionCache] Saved prompt state: ${u}`)}catch(e){console.warn(`[SessionCache] Failed to save prompt state: ${e.message}`)}let f={id:o,promptText:e,completionText:t,fullText:a,promptTokenCount:r,stateFilePath:c,stateFileSize:s.size,promptStatePath:u||null,promptStateSize:d,metadata:{...this.metadata},createdAt:new Date().toISOString(),lastAccessedAt:new Date().toISOString()};return this.cacheMap.entries[o]=f,this.cacheMap.totalSize+=s.size+d,this.requiresExactMatch()||await Ht(this.cacheMap,e,o,this.metadata),await Vt(this.cacheMap,this.maxSizeBytes,this.maxEntries),await Pt(this.cacheMap,this.baseDir),console.log(`[SessionCache] Saved entry: ${o} (${s.size} bytes, ${a.length} chars)`),f}catch(e){return console.warn(`[SessionCache] Failed to save state: ${e.message}`),s(),null}}async generateTempStatePath(){return await G(At(this.baseDir)),Lt(this.baseDir)}async cleanup(){await Ut(this.baseDir)}};const qt=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,t);if(!n.ok){let t=await n.text().catch(()=>``);throw Error(`Failed to fetch ${e}: ${n.status} ${n.statusText} ${t}`.trim())}return n.json()},Jt=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,{...t,method:`HEAD`});if(!n.ok)throw Error(`Failed to fetch headers for ${e}: ${n.status} ${n.statusText}`);return n},Yt=async(e,t,n=W)=>{let r=JSON.stringify({url:e,headers:t}),i=await Et(r,`range-metadata`,n);if(i)return i;let a=!/^https?:/i.test(e),{metadata:o}=await S(e,{fetch,additionalFetchHeaders:t,allowLocalFile:a});return await Dt(r,`range-metadata`,o,n),o},Xt=(e,t)=>{if(e.model.local_path)return l.resolve(e.model.local_path);let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},K=async(e,t)=>{try{let n=await v(e);return t?n.size===t:!0}catch{return!1}},Zt=async(e,t,n,r,i)=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);await G(l.dirname(n));let a=await fetch(e,{headers:t});if(!a.ok||!a.body)throw Error(`Failed to download ${e}: ${a.status} ${a.statusText}`);let o=await m(n,`w`),s=Number(a.headers.get(`content-length`))||r||0,c=0,u=.05;try{await a.body.pipeTo(new ot({async write(e){if(await o.write(e),c+=e.byteLength,typeof i==`function`&&s>0){let e=Math.min(1,c/s);for(;e>=u;)i(u),u+=.05}},async close(){await o.close(),typeof i==`function`&&i(1)},async abort(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}}))}catch(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}if(r){let e=await v(n);if(e.size!==r)throw await y(n).catch(()=>{}),Error(`Downloaded file size mismatch, expected ${r} got ${e.size}`)}},Qt=async e=>{let t=e.model.repo_id||e.model.repository||e.model.model;if(!t)throw Error("`model.repo_id` is required in Buttress backend config");let n=e.model.revision||`main`,r=e.runtime.cache_dir,i=JSON.stringify({repoId:t,revision:n,filename:e.model.filename,url:e.model.url,quantization:e.model.quantization,preferred_quantizations:e.model.preferred_quantizations}),a=await Et(i,`artifact-info`,r);if(a)return a;let o={...e.runtime.http_headers||{}};if(e.runtime.huggingface_token&&(o.Authorization=`Bearer ${e.runtime.huggingface_token}`),e.model.url){let a=await Jt(e.model.url,{headers:o}),s=Number(a.headers.get(`content-length`))||null,c={repoId:t,revision:n,filename:e.model.filename||e.model.url.split(`/`).pop(),url:e.model.url,size:s,headers:o};return await Dt(i,`artifact-info`,c,r),c}let{filename:s}=e.model,c=e.model.quantization&&String(e.model.quantization).toLowerCase(),l=await qt(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),u=l?.siblings||l?.files||[],d=[];for(let e of u){let t=e.rfilename||e.path||e.filename;typeof t==`string`&&t.endsWith(`.gguf`)&&d.push(t)}if(d.length===0)throw Error(`No GGUF artifacts found in repo ${t}`);let f=e.model.preferred_quantizations.length>0?e.model.preferred_quantizations:dt,p=d.map(e=>e.toLowerCase()),m=()=>{for(let e of f){let t=p.findIndex(t=>t.includes(e));if(t!==-1)return{filename:d[t],quantization:e}}return null};if(s)c||=St(s);else{let{filename:e,quantization:t}=m()||{filename:d[0],quantization:null};s=e,c=t||St(s)}let h=`${e.model.base_url.replace(/\/+$/,``)}/${t}/resolve/${n}/${s}`,g=/-(\d{5})-of-(\d{5})\.gguf$/,_=s.match(g),v=null;if(_){let[,,r]=_,i=await qt(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),a=i?.siblings||i?.files||[],c=Number(r);v=0;for(let e=1;e<=c;e+=1){let t=String(e).padStart(5,`0`),n=s.replace(g,`-${t}-of-${r}.gguf`),i=a.find(e=>(e.rfilename||e.path||e.filename)===n),o=Number(i?.size);Number.isFinite(o)&&o>0&&(v+=o)}}else{let e=await Jt(h,{headers:o});v=Number(e.headers.get(`content-length`))||null}let y={repoId:t,revision:n,filename:s,url:h,size:v,quantization:c,headers:o,isSplit:!!_,splitCount:_?Number(_[2]):0};return await Dt(i,`artifact-info`,y,r),y},$t=/^mmproj-.*\.gguf$/i,en=async(e,t)=>{if(!e.model.enable_mtmd)return null;let n=e.runtime.cache_dir,r={...e.runtime.http_headers||{}};e.runtime.huggingface_token&&(r.Authorization=`Bearer ${e.runtime.huggingface_token}`);let i=t?.repoId||e.model.repo_id,a=t?.revision||e.model.revision||`main`,o=JSON.stringify({kind:`mmproj`,repoId:i,revision:a,mmproj_filename:e.model.mmproj_filename,mmproj_url:e.model.mmproj_url,mmproj_local_path:e.model.mmproj_local_path}),s=await Et(o,`artifact-info`,n);if(s)return s;if(e.model.mmproj_url){let t=await Jt(e.model.mmproj_url,{headers:r}),s=Number(t.headers.get(`content-length`))||null,c={repoId:i,revision:a,filename:e.model.mmproj_filename||e.model.mmproj_url.split(`/`).pop(),url:e.model.mmproj_url,size:s,headers:r};return await Dt(o,`artifact-info`,c,n),c}if(e.model.mmproj_local_path){if(!e.model.allow_local_file)throw Error("`model.mmproj_local_path` requires `model.allow_local_file = true`");let t={repoId:i,revision:a,filename:l.basename(e.model.mmproj_local_path),url:null,size:null,headers:r,localPath:l.resolve(e.model.mmproj_local_path)};return await Dt(o,`artifact-info`,t,n),t}if(!i)throw Error("Cannot derive mmproj artifact without `model.repo_id`");let c=await qt(`${e.model.api_base}/models/${i}?revision=${a}&blobs=true`,{headers:r}),u=c?.siblings||c?.files||[],d=u.map(e=>e.rfilename||e.path||e.filename).filter(e=>typeof e==`string`),f=e.model.mmproj_filename;if(f){if(!d.includes(f))throw Error(`mmproj file "${f}" not found in repo ${i}`)}else{let e=d.filter(e=>$t.test(e));if(e.length===0)return console.warn(`[buttress] enable_mtmd set but no mmproj file found in ${i}; skipping multimodal load`),null;let n=t?.quantization&&String(t.quantization).toLowerCase();f=n&&e.find(e=>e.toLowerCase().includes(n))||e[0]}let p=`${e.model.base_url.replace(/\/+$/,``)}/${i}/resolve/${a}/${f}`,m=u.find(e=>(e.rfilename||e.path||e.filename)===f),h=Number(m?.size);if(!Number.isFinite(h)||h<=0){let e=await Jt(p,{headers:r});h=Number(e.headers.get(`content-length`))||null}let g={repoId:i,revision:a,filename:f,url:p,size:h,headers:r};return await Dt(o,`artifact-info`,g,n),g},tn=(e,t)=>{if(t?.localPath)return t.localPath;if(!t)return null;let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},nn=async(e,{modelBytes:t=null,kvCacheBytes:n=null}={})=>{let r=Ct(e),[i,...a]=r,o=e.backend?.gpu_memory_fraction==null?vt.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(e.backend.gpu_memory_fraction))),s=e.backend?.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),c=await ke({platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-llm`,variant:i||null,preferVariants:a,gpuMemoryFraction:o,cpuMemoryFraction:s,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:t,kvCacheBytes:n}),l=e=>({...e,devices:Array.isArray(e.devices)?e.devices:[],ok:e.ok,hasGpu:!!e.hasGpu,totalMemory:e.gpuTotalBytes||e.totalMemory||0,error:e.ok?null:Error(e.error||`Variant ${e.variant} not available on this platform`)});if(!c.ok||!c.selected){let e=(c.attempts||[]).map(e=>`${e.variant}: ${e.error||`unknown error`}`).join(`; `);throw Error(`Unable to initialize any backend variant (${r.join(`, `)}). Errors: ${e}`)}let u=(c.attempts||[]).map(l);return{selected:l(c.selected),attempts:u}},rn=async e=>{let t=await Qt(e),n=await en(e,t),r=await Yt(t.url,t.headers,e.runtime.cache_dir),{arch:i,nCtxTrain:a,nLayer:o,nEmbd:s,nHead:c,nHeadKv:l,nEmbdHeadK:u,nEmbdHeadV:d,quantVersion:f,fileType:p,attentionLayerCount:m,recurrentLayerCount:h,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C}=Ke(r),w=Number.isFinite(Number(o))?Number(o):0,T=Number.isFinite(Number(s))?Number(s):0,E=Number.isFinite(Number(c))?Number(c):0,D=Number.isFinite(Number(l))?Number(l):E,ee=E>0&&T>0?T/E:128,te=u!=null&&Number.isFinite(Number(u))?Number(u):ee,ne=d!=null&&Number.isFinite(Number(d))?Number(d):ee,O=ze({arch:i,metadata:r,nLayer:w}),re=O&&Number.isFinite(Number(O.kvLayers))?Number(O.kvLayers):w,k=Math.max(0,Math.floor(Number(re)||0)),A={use_mmap:e.model.use_mmap??e.runtime.use_mmap,use_mlock:e.model.use_mlock??e.runtime.use_mlock,no_extra_bufts:e.model.no_extra_bufts??e.runtime.no_extra_bufts,n_threads:e.model.n_threads??e.runtime.n_threads,n_ctx:e.model.n_ctx??e.runtime.n_ctx,n_batch:e.model.n_batch??e.runtime.n_batch,n_ubatch:e.model.n_ubatch??e.runtime.n_ubatch,n_cpu_moe:e.model.n_cpu_moe??e.runtime.n_cpu_moe,n_parallel:(e.model.n_parallel??e.runtime.n_parallel)||4,cpu_mask:e.model.cpu_mask??e.runtime.cpu_mask,cpu_strict:e.model.cpu_strict??e.runtime.cpu_strict,devices:e.model.devices??e.runtime.devices,n_gpu_layers:e.model.n_gpu_layers??e.runtime.n_gpu_layers,flash_attn_type:e.model.flash_attn_type??e.runtime.flash_attn_type,cache_type_k:e.model.cache_type_k??e.runtime.cache_type_k,cache_type_v:e.model.cache_type_v??e.runtime.cache_type_v,kv_unified:e.model.kv_unified??e.runtime.kv_unified,swa_full:e.model.swa_full??e.runtime.swa_full,ctx_shift:e.model.ctx_shift??e.runtime.ctx_shift,...ht(e)},j=A.n_ctx?Number(A.n_ctx):null,M=j||a||4096,N=[],P=[],ie=!0;if(j&&a&&j>a){ie=!1;let e=`Requested context length (${j}) exceeds model training context (${a})`;N.push(e),P.push(e),M=a}j&&!a&&N.push(`Model metadata missing training context length, using requested value`);let F={k:A.cache_type_k,v:A.cache_type_v},I=t.size>0?t.size:0,L=qe({layerCount:k,headKvCount:D,embdHeadKCount:te,embdHeadVCount:ne,cacheTypes:F,swaConfig:O,kvUnified:A.kv_unified,nParallel:A.n_parallel,swaFull:A.swa_full,arch:i,attentionLayerCount:m}),R=Je({nLayer:w,nEmbd:T,recurrentLayerCount:h,nSeqMax:A.n_parallel||4,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C,arch:i}),z=await nn(e,{modelBytes:I,kvCacheBytes:L(M)+R}),ae=z.selected.totalMemory||0,oe=ae*(e.backend.gpu_memory_fraction||1),se=e.backend.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),ce=Math.max(0,x.totalmem()*se),le=z.selected.hasGpu?oe:ce,B=Ye({maxCtx:M,availableMemory:le,modelBytes:I,kvBytesForCtx:L});if(!j&&B){let e=a?Math.min(B,a):B,t=Math.max(32,e);t<M&&N.push(`Context length capped to ${t} by memory limits`),M=t}M>B&&(M=B);let ue=Math.floor(B);console.log(`[buttress] Memory-limited context length: ${ue}`);let de=L(M),fe=I+de+R,pe=w?I/(w+1):I,me=0;z.selected.hasGpu&&pe>0&&(me=Math.min(w+1,Math.max(0,Math.floor(oe/pe)))),console.log(`[buttress] Auto GPU layer capacity (${z.selected.variant}): ${me}/${w+1}`);let he;he=A.n_gpu_layers===`auto`||A.n_gpu_layers==null?me:Math.max(0,Math.min(Number(A.n_gpu_layers)||0,w+1));let ge=(()=>{let e=A.flash_attn_type&&String(A.flash_attn_type).toLowerCase();return e===`on`||e===`off`?e:z.selected.hasGpu?`auto`:`off`})(),_e=e.runtime.cache_dir,ve=Xt(e,t),ye=await K(ve,t.size),be=tn(e,n),xe=be?await K(be,n?.size):!1,Se=n?{enabled:!0,initialized:!1,filename:n.filename,url:n.url,sizeBytes:n.size,localPath:be,exists:xe,useGpu:e.model.mmproj_use_gpu,imageMinTokens:e.model.mmproj_image_min_tokens,imageMaxTokens:e.model.mmproj_image_max_tokens}:{enabled:!1,requested:!!e.model.enable_mtmd};return{config:e,info:{ok:ie,backend:`ggml-llm`,warnings:N,errors:P,model:{repoId:t.repoId,revision:t.revision,filename:t.filename,quantization:t.quantization,url:t.url,sizeBytes:t.size,metadata:{architecture:i,n_ctx_train:a,n_layer:w,n_embd:T,quantization_version:f,file_type:p,kv_layer_count:k,swa:O?.enabled?{window:O.window,pattern:O.pattern,dense_first:O.denseFirst,type:O.type,layers:O.swaLayers}:null}},runtime:{...A,variant:z.selected.variant,n_ctx:M,requested_ctx:j,n_gpu_layers:he,auto_gpu_layers:me,flash_attn_type:ge,cache_type_k:F.k,cache_type_v:F.v,estimated_max_n_ctx:ue},resources:{modelBytes:I,kvCacheBytes:de,recurrentMemoryBytes:R,totalEstimatedBytes:fe,gpuCapacityBytes:ae,gpuUsableBytes:oe,cpuUsableBytes:ce,fit:z.selected.fit},devices:{selected:z.selected,attempts:z.attempts},download:{cacheDir:_e,localPath:ve,exists:ye},multimodal:Se,timestamp:new Date().toISOString()},artifact:t,mmprojArtifact:n,mmprojLocalPath:be,mmprojLocalExists:xe,metadata:{arch:i,nCtxTrain:a,nLayer:w,nEmbd:T},devices:z,cacheTypes:F,localPath:ve,localExists:ye}},an=(e,t,n=null,r=null)=>{let i,a=Date.now(),o=0;return new at({async start(s){try{let c=await e.parallel.completion(t,(e,t)=>{t&&(t.token&&(o+=1),s.enqueue({event:`token`,data:{requestId:e,...t}}))}),{requestId:l}=c;i=c.stop;let u=await c.promise;console.log(`[Completion] Result:`,u),s.enqueue({event:`result`,data:{requestId:l,...u}}),s.close();let d=Date.now()-a,f=u.timings||{};H.addCompletion({id:`completion-${l}`,generatorId:n,requestId:l,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:r?.variant||null,cacheTokens:f.cache_n??0,promptTokens:f.prompt_n??0,tokensGenerated:f.predicted_n??o,tokensPerSecond:f.predicted_per_second??0,promptPerSecond:f.prompt_per_second??0,durationMs:d,success:!0,interrupted:u.interrupted||!1,contextFull:u.context_full||u.contextFull||!1})}catch(e){s.enqueue({event:`error`,data:{message:e?.message||String(e)}}),s.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:n,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:r?.variant||null,durationMs:Date.now()-a,tokensGenerated:o,success:!1,error:e?.message||String(e)})}},cancel(){i&&i()}})},on=(e,t,n,r,i,a,o=null,s=null,c=null)=>{let l,u=``,d=!1,f=Date.now(),p=0,m=()=>{i&&y(i).catch(()=>{}),c&&y(c).catch(()=>{})};return new at({async start(h){try{let g=await e.parallel.completion(t,(e,t)=>{t&&(t.token&&(u+=t.token,p+=1),h.enqueue({event:`token`,data:{requestId:e,...t}}))}),{requestId:_}=g;l=g.stop;let v=await g.promise;v.text?u=v.text:v.content&&(u=v.content),d=!v.interrupted&&!v.context_full,console.log(`[Completion] Result:`,v),h.enqueue({event:`result`,data:{requestId:_,...v}}),h.close();let y=Date.now()-f,b=v.timings||{};H.addCompletion({id:`completion-${_}`,generatorId:o,requestId:_,repoId:s?.repoId||null,quantization:s?.quantization||null,variant:s?.variant||null,cacheTokens:b.cache_n??0,promptTokens:b.prompt_n??a??0,tokensGenerated:b.predicted_n??p,tokensPerSecond:b.predicted_per_second??0,promptPerSecond:b.prompt_per_second??0,durationMs:y,success:!0,interrupted:v.interrupted||!1,contextFull:v.context_full||v.contextFull||!1,usedCache:!!t.load_state_path}),d&&n.enabled&&u?n.saveCompletionState(r,u,i,a,c).catch(e=>{console.warn(`[SessionCache] Save failed:`,e.message)}):m()}catch(e){h.enqueue({event:`error`,data:{message:e?.message||String(e)}}),h.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:o,repoId:s?.repoId||null,quantization:s?.quantization||null,variant:s?.variant||null,durationMs:Date.now()-f,tokensGenerated:p,success:!1,error:e?.message||String(e)}),m()}},cancel(){l&&l(),m()}})},sn=e=>{let t={model:e.plan.localPath,runtime:e.plan.info.runtime};return s(`sha256`).update(JSON.stringify(t)).digest(`hex`).slice(0,24)},cn=async(e,t,n,r=null)=>{let{config:i,localPath:a,artifact:o}=e;if(e.localExists&&!t.has(a))return e.info.download.exists=!0,typeof n==`function`&&n(.5),a;if(i.model.local_path&&!i.model.allow_local_file)throw Error("Local model path provided but `model.allow_local_file` is not enabled");let s=a;if(r){let t=r.getDownload(s);if(t){console.log(`[ensureModelFile] Waiting for global download: ${o.repoId}`);try{if(await t,await K(a,o.size))return e.localExists=!0,e.info.download.exists=!0,typeof n==`function`&&n(.5),a}catch(e){console.warn(`[ensureModelFile] Global download failed, will retry: ${e.message}`)}}}t.has(s)||t.set(s,(async()=>{if(o.isSplit&&o.splitCount>0){let e=/-(\d{5})-of-(\d{5})\.gguf$/,t=l.dirname(a),r=o.splitCount,s=0;for(let a=1;a<=r;a+=1){let c=String(a).padStart(5,`0`),u=o.filename.replace(e,`-${c}-of-${String(r).padStart(5,`0`)}.gguf`),d=`${i.model.base_url.replace(/\/+$/,``)}/${o.repoId}/resolve/${o.revision}/${u}`,f=l.join(t,u);await K(f)||await Zt(d,o.headers,f,null,e=>{if(e>=0&&Number.isFinite(e)){let t=(s+e)/r,i=Math.round(t*100);console.log(`Downloading model splits: ${Math.min(100,i)}%`),typeof n==`function`&&n(t*.5)}}),s+=1}}else console.log(`Downloading model: 0%`),await Zt(o.url,o.headers,a,o.size,e=>{if(e>=0&&Number.isFinite(e)){let t=Math.round(e*100);console.log(`Downloading model: ${Math.min(100,t)}%`),typeof n==`function`&&n(e*.5)}});e.localExists=!0,e.info.download.exists=!0})());try{await t.get(s)}finally{t.delete(s)}return a},ln=async(e,t,n,r=null)=>{let{mmprojArtifact:i,mmprojLocalPath:a}=e;if(!i||!a)return null;if(i.localPath){if(!await K(a))throw Error(`mmproj local file not found: ${a}`);return e.mmprojLocalExists=!0,e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a}if(e.mmprojLocalExists&&!t.has(a))return e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a;let o=a;if(r){let t=r.getDownload(o);if(t)try{if(await t,await K(a,i.size))return e.mmprojLocalExists=!0,e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a}catch(e){console.warn(`[ensureMmprojFile] Global download failed, will retry: ${e.message}`)}}t.has(o)||t.set(o,(async()=>{console.log(`Downloading mmproj: 0%`),await Zt(i.url,i.headers,a,i.size,e=>{if(e>=0&&Number.isFinite(e)){let t=Math.round(e*100);console.log(`Downloading mmproj: ${Math.min(100,t)}%`),typeof n==`function`&&n(e)}}),e.mmprojLocalExists=!0,e.info.multimodal.exists=!0})());try{await t.get(o)}finally{t.delete(o)}return a},un=async(e,t)=>{let n=sn(e),r=e.contexts.get(n);if(r&&!r.released)return r.releaseTimer&&(clearTimeout(r.releaseTimer),r.releaseTimer=null,console.log(`[Context] Cancelled pending release for context "${n}"`)),r.releaseRequested=!1,r.refCount+=1,console.log(`[Context] Reusing existing context "${n}", refCount=${r.refCount}`),typeof t==`function`&&t(0),r.context||await r.ready,typeof t==`function`&&t(1),r;r?console.log(`[Context] Record exists but released=${r.released}, creating new context`):console.log(`[Context] No existing record for "${n}", creating new context`),r={key:n,refCount:1,ready:null,released:!1},e.contexts.set(n,r),r.ready=(async()=>{let i=Date.now(),a=await cn(e.plan,e.downloads,t,e.globalDownloadManager);typeof t==`function`&&t(.5);let o={model:a,n_threads:e.plan.info.runtime.n_threads,use_mmap:e.plan.info.runtime.use_mmap,use_mlock:e.plan.info.runtime.use_mlock,no_extra_bufts:e.plan.info.runtime.no_extra_bufts,cpu_mask:e.plan.info.runtime.cpu_mask,cpu_strict:e.plan.info.runtime.cpu_strict,devices:e.plan.info.runtime.devices,n_ctx:e.plan.info.runtime.n_ctx,n_gpu_layers:e.plan.info.runtime.n_gpu_layers,n_parallel:e.plan.info.runtime.n_parallel,n_batch:e.plan.info.runtime.n_batch,n_ubatch:e.plan.info.runtime.n_ubatch,n_cpu_moe:e.plan.info.runtime.n_cpu_moe,flash_attn_type:e.plan.info.runtime.flash_attn_type,ctx_shift:e.plan.info.runtime.ctx_shift,kv_unified:e.plan.info.runtime.kv_unified,swa_full:e.plan.info.runtime.swa_full,lib_variant:e.plan.info.runtime.variant};for(let t of pt){let n=e.plan.info.runtime[t];n!=null&&(o[t]=n)}e.plan.info.runtime.flash_attn_type!==`off`&&(o.cache_type_k=e.plan.info.runtime.cache_type_k,o.cache_type_v=e.plan.info.runtime.cache_type_v),console.log(`[Context] Load Options:`,o);let s;try{if(s=await T(o,e=>{typeof t==`function`&&(t(.5+e*.25),e%5==0&&console.log(`[Context] Load Model Progress:`,e))}),e.plan.info.runtime.n_parallel&&!await s.parallel.enable({n_parallel:e.plan.info.runtime.n_parallel,n_batch:e.plan.info.runtime.n_batch}))throw Error(`Failed to enable parallel decoding mode for context`);if(e.plan.mmprojArtifact){let t=await ln(e.plan,e.downloads,null,e.globalDownloadManager);if(t){let n=e.config.model.mmproj_use_gpu,r={path:t,use_gpu:n==null?(e.plan.info.runtime.n_gpu_layers||0)>0:!!n,image_min_tokens:e.config.model.mmproj_image_min_tokens,image_max_tokens:e.config.model.mmproj_image_max_tokens};console.log(`[Context] initMultimodal:`,r),await s.initMultimodal(r)?e.plan.info.multimodal.initialized=!0:console.warn(`[Context] initMultimodal returned false; multimodal disabled`)}}return typeof t==`function`&&t(1),r.context=s,r.modelInfo=s.getModelInfo(),H.addModelLoad({id:`${e.id}-${n}`,generatorId:e.id,contextKey:n,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,variant:e.plan.info.runtime?.variant||null,nCtx:e.plan.info.runtime?.n_ctx||null,nGpuLayers:e.plan.info.runtime?.n_gpu_layers||null,durationMs:Date.now()-i,success:!0}),r}catch(t){if(H.addModelLoad({id:`${e.id}-${n}`,generatorId:e.id,contextKey:n,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,variant:e.plan.info.runtime?.variant||null,durationMs:Date.now()-i,success:!1,error:t?.message||String(t)}),s)try{s.release()}catch{}throw t}})();try{return await r.ready,r}catch(t){throw e.contexts.delete(n),t}},dn=async(e,t,n=!1)=>{if(t.released||!n&&t.refCount>0)return!1;t.released=!0,e.contexts.delete(t.key);try{t.context?.parallel?.disable?.()}catch{}return await t.context?.release?.(),!0},fn=async(e,t,n=!1)=>{if(t.releaseRequested=!0,t.releaseTimer&&=(clearTimeout(t.releaseTimer),null),n)t.refCount=0;else if(t.refCount=Math.max(0,t.refCount-1),t.refCount>0)return t.releaseRequested=!1,!1;let r=e.config.runtime.context_release_delay_ms;if(typeof r!=`number`||!Number.isFinite(r))return dn(e,t);let i=Math.max(0,Math.floor(r));return n||i<=0?dn(e,t):(console.log(`[Context] Scheduling release in ${i}ms for context "${t.key}"`),t.releaseTimer=setTimeout(async()=>{if(t.releaseTimer=null,t.refCount>0){console.log(`[Context] Release cancelled, refCount=${t.refCount} for context "${t.key}"`),t.releaseRequested=!1;return}console.log(`[Context] Releasing context "${t.key}" after ${i}ms delay`),await dn(e,t)},i),!0)};async function pn(e,t,n={}){let{globalDownloadManager:r=null}=n,i=xt(t),a=await rn(i),o=new Kt(i,a);await o.initialize();let s={id:e,type:`ggml-llm`,config:i,plan:a,info:a.info,contexts:new Map,downloads:new Map,globalDownloadManager:r,sessionCache:o,finalized:!1};return{id:e,type:`ggml-llm`,info:a.info,contexts:s.contexts,initContext:async(e={})=>{let{onProgress:t}=e,n=await un(s,t);return s.sessionCache.updateModelInfo(n.modelInfo),{modelInfo:n.modelInfo?{...n.modelInfo}:null,runtime:{...s.plan.info.runtime},download:{...s.plan.info.download},multimodal:s.plan.info.multimodal?{...s.plan.info.multimodal}:null}},completion:async(e={})=>{let{options:t={},useCache:n=!0}=e,r=_t(t,s.plan.info.runtime),i=sn(s),a=s.contexts.get(i);if(!a)throw Error(`Context "${i}" not initialized`);await a.ready;let o=r.prompt||``,c=null,l=null;if(!o&&r.messages){({messages:c}=r),l={chatTemplate:r.chat_template||r.chatTemplate,jinja:r.jinja??!0,tools:r.tools,parallel_tool_calls:r.parallel_tool_calls,tool_choice:r.tool_choice,reasoning_format:r.reasoning_format,enable_thinking:r.enable_thinking,add_generation_prompt:r.add_generation_prompt,now:r.now,chat_template_kwargs:r.chat_template_kwargs,force_pure_content:r.force_pure_content};let e=await a.context.getFormattedChat(c,l.chatTemplate,l);o=e?.prompt||e||``}if(n&&s.sessionCache.enabled&&o){let{options:e}=await s.sessionCache.prepareCompletionOptions(r,o,a.context),t=await s.sessionCache.generateTempStatePath(),n=(await a.context.tokenize(o))?.tokens?.length||0,i={...e,save_state_path:t},c=s.sessionCache.requiresExactMatch(),l=!!i.load_state_path,u=null;c&&!l&&(u=await s.sessionCache.generateTempStatePath(),i.save_prompt_state_path=u);let d={repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null};return on(a.context,i,s.sessionCache,o,t,n,s.id,d,u)}let u={repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null};return an(a.context,r,s.id,u)},tokenize:async(e={})=>{let{text:t=``,params:n={}}=e,r=sn(s),i=s.contexts.get(r);if(!i)throw Error(`Context "${r}" not initialized`);await i.ready;let a=await i.context.tokenize(t,n);if(!a)return{tokens:[]};let o=Array.from(a.tokens??[],Number);return{...a,tokens:o}},detokenize:async(e={})=>{let{tokens:t=[]}=e,n=sn(s),r=s.contexts.get(n);if(!r)throw Error(`Context "${n}" not initialized`);await r.ready;let i=t.map(e=>Number(e));return r.context.detokenize(i)},applyChatTemplate:async(e={})=>{let{messages:t=[],template:n,params:r}=e,i=sn(s),a=s.contexts.get(i);if(!a)throw Error(`Context "${i}" not initialized`);return await a.ready,await a.context.getFormattedChat(t,n,r)},releaseContext:async()=>{if(s.finalized)return!1;let e=sn(s),t=s.contexts.get(e);return t?fn(s,t,!1):!1},finalize:async()=>{if(s.finalized)return;s.finalized=!0;let e=Array.from(s.contexts.values()),t=e.map(e=>e.released||e.releaseRequested||e.releaseTimer||(e.refCount=Math.max(0,e.refCount-1),e.refCount>0)?Promise.resolve(!1):dn(s,e));await Promise.allSettled(t),(e.length===0||e.every(e=>e.released))&&await s.sessionCache.cleanup()},getStatus:()=>{let e=[],t=Array.from(s.contexts.entries()).map(([t,n])=>{let r={key:t,refCount:n.refCount,hasModel:!!n.context},i=n.context.parallel.getStatus();return r.parallelStatus=i,e.push({contextKey:t,...i}),r});return{id:s.id,type:s.type,repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null,nCtx:s.plan.info.runtime?.n_ctx||null,nParallel:s.plan.info.runtime?.n_parallel||null,contexts:t,parallelStatuses:e}},subscribeParallelStatus:e=>{let t=Array.from(s.contexts.entries()).map(([t,n])=>n.context.parallel.subscribeToStatus(n=>{e({contextKey:t,...n})}));return{remove:()=>{t.forEach(e=>{e?.remove&&e.remove()})}}},hasPendingReleases:()=>Array.from(s.contexts.values()).some(e=>!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0)),resetFinalized:()=>{s.finalized=!1}}}const mn=e=>{let t=xt(e);return t.model.repo_id||t.model.repository||t.model.model||null};async function hn(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n;try{let n=xt(e),o=await Qt(n),s=Xt(n,o),{repoId:c}=o,u=await en(n,o).catch(e=>(console.warn(`[Download] Failed to derive mmproj artifact: ${e.message}`),null)),d=tn(n,u),f=async()=>{if(!u||!d||u.localPath)return;if(await K(d,u.size)){console.log(`[Download] mmproj already exists: ${d}`);return}let e=t.getDownload(d);if(e){await e;return}let n=(async()=>{try{await Zt(u.url,u.headers,d,u.size,e=>{e>=0&&Number.isFinite(e)&&console.log(`[Download] mmproj ${c}: ${Math.round(e*100)}%`)})}finally{t.deleteDownload(d)}})();t.setDownload(d,n),await n};if(await K(s,o.size))return console.log(`[Download] Model already exists: ${c} at ${s}`),await f().catch(e=>{console.error(`[Download] mmproj download failed: ${e.message}`),typeof a==`function`&&a(e)}),typeof i==`function`&&i({localPath:s,repoId:c,alreadyExists:!0}),{started:!1,localPath:s,repoId:c,alreadyExists:!0};let p=t.getDownload(s);if(p)return console.log(`[Download] Already downloading: ${c}`),p.then(()=>{typeof i==`function`&&i({localPath:s,repoId:c,joinedExisting:!0})}).catch(e=>{typeof a==`function`&&a(e)}),{started:!1,localPath:s,repoId:c,alreadyDownloading:!0};console.log(`[Download] Starting download: ${c}`);let m=(async()=>{try{if(o.isSplit&&o.splitCount>0){let e=/-(\d{5})-of-(\d{5})\.gguf$/,t=l.dirname(s),i=o.splitCount,a=0;for(let s=1;s<=i;s+=1){let u=String(s).padStart(5,`0`),d=o.filename.replace(e,`-${u}-of-${String(i).padStart(5,`0`)}.gguf`),f=`${n.model.base_url.replace(/\/+$/,``)}/${o.repoId}/resolve/${o.revision}/${d}`,p=l.join(t,d);await K(p)||await Zt(f,o.headers,p,null,e=>{if(e>=0&&Number.isFinite(e)){let t=(a+e)/i;console.log(`[Download] ${c}: ${Math.round(t*100)}%`),typeof r==`function`&&r(t)}}),a+=1}}else await Zt(o.url,o.headers,s,o.size,e=>{e>=0&&Number.isFinite(e)&&(console.log(`[Download] ${c}: ${Math.round(e*100)}%`),typeof r==`function`&&r(e))});await f(),console.log(`[Download] Completed: ${c}`),typeof i==`function`&&i({localPath:s,repoId:c})}catch(e){throw console.error(`[Download] Failed: ${c}`,e.message),typeof a==`function`&&a(e),e}finally{t.deleteDownload(s)}})();return t.setDownload(s,m),{started:!0,localPath:s,repoId:c}}catch(e){return console.error(`[Download] Failed to start download:`,e.message),typeof a==`function`&&a(e),{started:!1,localPath:null,repoId:null,error:e.message}}}async function gn(e){let t=xt(e),n=await Qt(t),r=await Yt(n.url,n.headers,t.runtime.cache_dir),{arch:i,nCtxTrain:a,nLayer:o,nEmbd:s,nHead:c,nHeadKv:l,nEmbdHeadK:u,nEmbdHeadV:d,quantVersion:f,fileType:p,attentionLayerCount:m,recurrentLayerCount:h,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C}=Ke(r),w=Number.isFinite(Number(o))?Number(o):0,T=Number.isFinite(Number(s))?Number(s):0,E=Number.isFinite(Number(c))?Number(c):0,D=Number.isFinite(Number(l))?Number(l):E,ee=E>0&&T>0?T/E:128,te=u!=null&&Number.isFinite(Number(u))?Number(u):ee,ne=d!=null&&Number.isFinite(Number(d))?Number(d):ee,O=ze({arch:i,metadata:r,nLayer:w}),re=O&&Number.isFinite(Number(O.kvLayers))?Number(O.kvLayers):w,k=Math.max(0,Math.floor(Number(re)||0)),A=(t.model.n_ctx?Number(t.model.n_ctx):null)||a||4096,j={k:t.model.cache_type_k,v:t.model.cache_type_v},M=n.size>0?n.size:0,N=t.model.n_parallel||4,P=qe({layerCount:k,headKvCount:D,embdHeadKCount:te,embdHeadVCount:ne,cacheTypes:j,swaConfig:O,kvUnified:t.model.kv_unified,nParallel:N,swaFull:t.model.swa_full,arch:i,attentionLayerCount:m}),ie=Je({nLayer:w,nEmbd:T,recurrentLayerCount:h,nSeqMax:N,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C,arch:i}),F=t.backend?.gpu_memory_fraction==null?vt.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(t.backend.gpu_memory_fraction))),I=t.backend?.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(t.backend.cpu_memory_fraction))),L=await nn(t,{modelBytes:M,kvCacheBytes:P(A)}),R=(L.selected.totalMemory||0)*F,z=Math.max(0,x.totalmem()*I),ae=Ye({maxCtx:A,availableMemory:L.selected.hasGpu?R:z,modelBytes:M,kvBytesForCtx:P}),oe=P(A),se=P(ae);return{kvInfo:{nCtxTrain:a,nLayer:w,nEmbd:T,nHeadKv:D,nEmbdHeadK:te,nEmbdHeadV:ne,nHeadCount:E,nHeadKvCount:D,kvLayerCount:k,swa:O?.enabled?{window:O.window,pattern:O.pattern,denseFirst:O.denseFirst,type:O.type,layers:O.swaLayers}:null},modelBytes:M,kvCacheBytes:oe,limitedKvCacheBytes:se,memoryLimitedCtx:ae,recurrentMemoryBytes:ie,quantization:{name:n.quantization||null,fileType:p,version:f}}}const _n=e=>e?typeof e.score==`number`&&Number.isFinite(e.score)?Number(e.score):ue(e):0;async function vn(e=null,t={}){let{threshold:n=1.1,includeBreakdown:r=!1,config:i,...a}=t,o=null,s=null,c=null,l=null,u=null,d=null,f=null;if(i)try{let{modelBytes:e,kvCacheBytes:t,limitedKvCacheBytes:n,memoryLimitedCtx:r,recurrentMemoryBytes:a,kvInfo:p,quantization:m}=await gn(i);o=e,s=t,c=n,l=r,u=a,d=p,f=m}catch{}let p=i?.backend?.gpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.gpu_memory_fraction))),m=i?.backend?.cpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.cpu_memory_fraction))),h=await ke({...a,platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-llm`,includeBreakdown:r,gpuMemoryFraction:p,cpuMemoryFraction:m,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:o,kvCacheBytes:s,limitedKvCacheBytes:c}),g=h.selected,_=_n(g);g.modelBytes=o||null,g.kvCacheBytes=s||null,g.memoryLimitedCtx=l||null,g.limitedKvCacheBytes=c||null,g.recurrentMemoryBytes=u||null,g.kvInfo=d||null,g.quantization=f||null;let v=null,y=null;if(e){let t=_n(e);y={...e,score:t};let r=`buttress`,i=`buttress-higher-score`;if(!h.ok)r=`local`,i=`buttress-unavailable`;else if(!t&&t!==0)r=`buttress`,i=`missing-client-score`;else{let e=y.fit,a=y.limitedFit,o=g?.fit,s=g?.limitedFit,c=e?.fitsInGpu||e?.fitsInCpu||a?.fitsInGpu||a?.fitsInCpu,l=o?.fitsInGpu||o?.fitsInCpu||s?.fitsInGpu||s?.fitsInCpu;c&&!l?(r=`local`,i=`client-fits-in-memory`):l&&!c?(r=`buttress`,i=`buttress-fits-in-memory`):t>_*n?(r=`local`,i=`client-better`):_>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`)}v={buttressScore:_,clientScore:t,threshold:n,recommendation:r,reason:i}}!h.ok&&!v&&(v={buttressScore:_,clientScore:e?.score??null,threshold:n,recommendation:`local`,reason:`buttress-unavailable`});let b=null;return i&&(b={repoId:i.model?.repo_id||null,quantization:i.model?.quantization||null,nCtx:i.model?.n_ctx||null,cacheKType:i.model?.cache_type_k||`f16`,cacheVType:i.model?.cache_type_v||`f16`}),{type:`ggml-llm`,timestamp:new Date().toISOString(),buttress:h,client:y,comparison:v,modelConfig:b}}const{WritableStream:yn}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,bn=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),bn(e[t],n)):e[t]=n}),e),xn=`https://huggingface.co`,Sn=`https://huggingface.co/api`,Cn=l.join(x.homedir(),`.buttress`,`models`),wn=[`cuda`,`vulkan`,`default`],Tn=[`q8_0`,`q5_1`,`q5_0`,`q4_1`,`q4_0`],En=`fp16`,Dn=.5,On=[`large-v3-turbo`,`distil-large-v3`,`large-v3`,`large-v2`,`large-v1`,`large`,`distil-medium`,`medium.en`,`medium`,`small.en-tdrz`,`distil-small.en`,`small.en`,`small`,`base.en`,`base`,`tiny.en`,`tiny`],kn=e=>{if(!e)return null;let t=e.toLowerCase();return On.find(e=>t.includes(e))||null},An={backend:{type:`ggml-stt`,variant:null,variant_preference:wn,gpu_memory_fraction:.85,cpu_memory_fraction:Dn},model:{repo_id:`BricksDisplay/whisper-ggml`,revision:`main`,filename:null,url:null,quantization:null,preferred_quantizations:[`q8_0`,En,`q5_1`],allow_local_file:!1,local_path:null,api_base:Sn,base_url:xn,use_gpu:!0,use_flash_attn:`auto`},runtime:{cache_dir:Cn,prefer_variants:[],huggingface_token:process.env.HUGGINGFACE_TOKEN||null,http_headers:{},max_threads:null,context_release_delay_ms:1e4}},jn=(e,t=[])=>!e&&e!==0?[...t]:Array.isArray(e)?e.filter(e=>e!=null):[e],Mn=e=>{if(!e)return null;let t=String(e).toLowerCase();return[`cuda`,`vulkan`,`default`].includes(t)?t:null},Nn=(e={})=>{let t=structuredClone(An);if(bn(t,e),t.backend.variant=Mn(t.backend.variant),t.backend.variant_preference=Array.from(new Set(jn(t.backend.variant_preference||wn).flatMap(e=>{let t=Mn(e);return t?[t]:[]}))),t.backend.variant_preference.length===0&&(t.backend.variant_preference=[...wn]),t.runtime.prefer_variants=Array.from(new Set(jn(t.runtime.prefer_variants).flatMap(e=>{let t=Mn(e);return t?[t]:[]}))),t.model.preferred_quantizations=Array.from(new Set(jn(t.model.preferred_quantizations||t.model.quantizations).flatMap(e=>{let t=e?String(e).toLowerCase():null;return t?[t]:[]}))),t.model.quantization){let e=String(t.model.quantization).toLowerCase();t.model.preferred_quantizations.includes(e)||t.model.preferred_quantizations.unshift(e)}return t.model.base_url=t.model.base_url||xn,t.model.api_base=t.model.api_base||Sn,t.runtime.cache_dir=t.runtime.cache_dir?l.resolve(t.runtime.cache_dir):Cn,t.runtime.context_release_delay_ms=Math.max(0,Number(t.runtime.context_release_delay_ms)||An.runtime.context_release_delay_ms),t},Pn=e=>{let t=e.toLowerCase();return Tn.find(e=>t.includes(e))||null},Fn=e=>{let t=[];e.backend.variant&&t.push(e.backend.variant),e.runtime.prefer_variants.length>0&&t.push(...e.runtime.prefer_variants),t.push(...e.backend.variant_preference),t.push(`default`);let n=new Set;for(let e of t){let t=Mn(e);t&&n.add(t)}return Array.from(n)},In=async e=>{await p(e,{recursive:!0})},Ln=(e=Cn)=>l.join(e,`.metadata-cache`),Rn=(e,t,n=Cn)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(Ln(n),t,`${r}.json`)},zn=async(e,t,n=Cn)=>{try{let r=await h(Rn(e,t,n),`utf-8`);return JSON.parse(r)}catch{return null}},Bn=async(e,t,n,r=Cn)=>{try{let i=Rn(e,t,r);await In(l.dirname(i)),await b(i,JSON.stringify(n),`utf-8`)}catch{}},Vn=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,t);if(!n.ok){let t=await n.text().catch(()=>``);throw Error(`Failed to fetch ${e}: ${n.status} ${n.statusText} ${t}`.trim())}return n.json()},Hn=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,{...t,method:`HEAD`});if(!n.ok)throw Error(`Failed to fetch headers for ${e}: ${n.status} ${n.statusText}`);return n},Un=(e,t)=>{if(e.model.local_path)return l.resolve(e.model.local_path);let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},Wn=async(e,t)=>{try{let n=await v(e);return t?n.size===t:!0}catch{return!1}},Gn=async(e,t,n,r,i)=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);await In(l.dirname(n));let a=await fetch(e,{headers:t});if(!a.ok||!a.body)throw Error(`Failed to download ${e}: ${a.status} ${a.statusText}`);let o=await m(n,`w`),s=Number(a.headers.get(`content-length`))||r||0,c=0,u=.05;try{await a.body.pipeTo(new yn({async write(e){if(await o.write(e),c+=e.byteLength,typeof i==`function`&&s>0){let e=Math.min(1,c/s);for(;e>=u;)i(u),u+=.05}},async close(){await o.close(),typeof i==`function`&&i(1)},async abort(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}}))}catch(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}if(r){let e=await v(n);if(e.size!==r)throw await y(n).catch(()=>{}),Error(`Downloaded file size mismatch, expected ${r} got ${e.size}`)}},Kn=async e=>{let t=e.model.repo_id||e.model.repository||e.model.model;if(!t)throw Error("`model.repo_id` is required in Buttress backend config");let n=e.model.revision||`main`,r=e.runtime.cache_dir,i=JSON.stringify({repoId:t,revision:n,filename:e.model.filename,url:e.model.url,quantization:e.model.quantization,preferred_quantizations:e.model.preferred_quantizations}),a=await zn(i,`artifact-info`,r);if(a)return a;let o={...e.runtime.http_headers||{}};if(e.runtime.huggingface_token&&(o.Authorization=`Bearer ${e.runtime.huggingface_token}`),e.model.url){let a=await Hn(e.model.url,{headers:o}),s=Number(a.headers.get(`content-length`))||null,c=e.model.filename||e.model.url.split(`/`).pop(),l={repoId:t,revision:n,filename:c,url:e.model.url,size:s,quantization:Pn(c||``),headers:o};return await Bn(i,`artifact-info`,l,r),l}let{filename:s}=e.model,c=e.model.quantization&&String(e.model.quantization).toLowerCase(),l=await Vn(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),u=(l?.siblings||l?.files||[]).map(e=>e.rfilename||e.path||e.filename).filter(e=>typeof e==`string`&&e.endsWith(`.bin`));if(u.length===0)throw Error(`No model artifacts found in repo ${t}`);let d=e.model.preferred_quantizations.length>0?e.model.preferred_quantizations:Tn,f=()=>{for(let e of d)if(e===En){let e=u.find(e=>{let t=e.toLowerCase();return!Tn.some(e=>t.includes(e))});if(e)return{filename:e,quantization:null}}else{let t=u.find(t=>t.toLowerCase().includes(e));if(t)return{filename:t,quantization:e}}return null};if(s)c||=Pn(s);else{let{filename:e,quantization:t}=f()||{filename:u[0],quantization:null};s=e,c=t||Pn(s)}let p=`${e.model.base_url.replace(/\/+$/,``)}/${t}/resolve/${n}/${s}`,m=await Hn(p,{headers:o}),h=Number(m.headers.get(`content-length`))||null,g={repoId:t,revision:n,filename:s,url:p,size:h,quantization:c,headers:o,isSplit:!1,splitCount:0};return await Bn(i,`artifact-info`,g,r),g},qn=async(e,{modelBytes:t=null,processingBytes:n=null}={})=>{let r=Fn(e),[i,...a]=r,o=e.backend?.gpu_memory_fraction==null?An.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(e.backend.gpu_memory_fraction))),s=e.backend?.cpu_memory_fraction==null?Dn:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),c=await ke({platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-stt`,variant:i||null,preferVariants:a,variantPreference:e.backend.variant_preference,gpuMemoryFraction:o,cpuMemoryFraction:s,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:t,kvCacheBytes:n}),l=e=>({...e,devices:Array.isArray(e.devices)?e.devices:[],ok:e.ok,hasGpu:!!e.hasGpu,totalMemory:e.gpuTotalBytes||e.totalMemory||0,error:e.ok?null:Error(e.error||`Variant ${e.variant} not available on this platform`)});if(!c.ok||!c.selected){let e=(c.attempts||[]).map(e=>`${e.variant}: ${e.error||`unknown error`}`).join(`; `);throw Error(`Unable to initialize any backend variant (${r.join(`, `)}). Errors: ${e}`)}let u=(c.attempts||[]).map(l);return{selected:l(c.selected),attempts:u}},Jn=async e=>{let t=await Kn(e),n=Ne({modelBytes:t.size>0?t.size:0}),r=await qn(e,{modelBytes:n.modelBytes,processingBytes:n.processingBufferBytes}),i=r.selected.hasGpu&&(r.selected.fit?.fitsInGpu===void 0?!0:r.selected.fit.fitsInGpu);e.model.use_gpu===!1&&(i=!1);let a=e.model.use_flash_attn&&String(e.model.use_flash_attn).toLowerCase(),o;o=a===`on`||a===`true`?!0:a===`off`||a===`false`?!1:i;let s=e.runtime.cache_dir,c=Un(e,t),l=await Wn(c,t.size);return{config:e,info:{ok:!0,backend:`ggml-stt`,model:{repoId:t.repoId,revision:t.revision,filename:t.filename,quantization:t.quantization,modelType:kn(t.filename),url:t.url,sizeBytes:t.size},runtime:{variant:r.selected.variant,use_gpu:i,use_flash_attn:o,max_threads:e.runtime.max_threads?Number(e.runtime.max_threads):null},resources:{...n,gpuCapacityBytes:r.selected.gpuTotalBytes,gpuUsableBytes:r.selected.gpuUsableBytes,cpuUsableBytes:r.selected.cpuUsableBytes,fit:r.selected.fit},devices:{selected:r.selected,attempts:r.attempts},download:{cacheDir:s,localPath:c,exists:l},timestamp:new Date().toISOString()},artifact:t,memory:n,devices:r,localPath:c,localExists:l}},Yn=async(e,t,n,r=null)=>{let{localPath:i,artifact:a,config:o}=e;if(e.localExists)return typeof n==`function`&&n(1),i;if(r){let t=r.getDownload(i);if(t){console.log(`[ensureModelFile] Waiting for global STT download: ${a.repoId}`);try{if(await t,await Wn(i,a.size))return e.localExists=!0,e.info.download.exists=!0,typeof n==`function`&&n(1),i}catch(e){console.warn(`[ensureModelFile] Global STT download failed, will retry: ${e.message}`)}}}let s=t.get(i);if(s)return await s,typeof n==`function`&&n(1),i;let c=(async()=>{if(o.model.allow_local_file){if(!await Wn(i,a.size))throw Error(`Local model file not found: ${i}`);return i}return await Gn(a.url,a.headers,i,a.size,n),i})();t.set(i,c);try{return await c,i}finally{t.delete(i)}};var Xn=class{constructor(){this.queue=[],this.processing=!1,this.currentTaskId=null}async enqueue(e,t=null){return new Promise((n,r)=>{this.queue.push({task:e,resolve:n,reject:r,taskId:t}),this.processNext()})}async processNext(){if(this.processing||this.queue.length===0)return;this.processing=!0;let{task:e,resolve:t,reject:n,taskId:r}=this.queue.shift();this.currentTaskId=r;try{t(await e())}catch(e){n(e)}finally{this.processing=!1,this.currentTaskId=null,this.processNext()}}getStatus(){return{processing:this.processing,queuedCount:this.queue.length,currentTaskId:this.currentTaskId}}};const Zn=e=>{if(!e)return null;if(e instanceof ArrayBuffer)return e;if(ArrayBuffer.isView(e))return e.buffer;if(typeof e==`string`){let t=e.startsWith(`data:`)?e.split(`,`)[1]||``:e,n=Buffer.from(t,`base64`);return n.buffer.slice(n.byteOffset,n.byteOffset+n.byteLength)}throw Error(`Unsupported audioData format, expected base64 string or ArrayBuffer`)},Qn=async(e,t)=>{if(e.contextRecord&&!e.contextRecord.released)return e.contextRecord.releaseTimer&&(clearTimeout(e.contextRecord.releaseTimer),e.contextRecord.releaseTimer=null,console.log(`[Context] Cancelled pending STT release`)),e.contextRecord.releaseRequested=!1,e.contextRecord.refCount+=1,console.log(`[Context] Reusing existing STT context, refCount=${e.contextRecord.refCount}`),typeof t==`function`&&t(0),e.contextRecord.context||await e.contextRecord.ready,typeof t==`function`&&t(1),e.contextRecord;e.contextRecord?console.log(`[Context] STT record exists but released=${e.contextRecord.released}, creating new context`):console.log(`[Context] No existing STT record, creating new context`);let n={refCount:1,ready:null,released:!1};e.contextRecord=n,n.ready=(async()=>{let r=Date.now();try{typeof t==`function`&&t(0);let i=await Yn(e.plan,e.downloads,t,e.globalDownloadManager);typeof t==`function`&&t(.5);let a=await ee({filePath:i,useFlashAttn:e.plan.info.runtime.flash_attn_type===`on`,useGpu:e.plan.info.runtime.n_gpu_layers>0,nThreads:e.plan.info.runtime.n_threads},e.plan.info.runtime.variant);typeof t==`function`&&t(1),n.context=a;try{n.modelInfo=a.getModelInfo()}catch{n.modelInfo=null}return U.addModelLoad({id:e.id,generatorId:e.id,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,modelType:e.plan.info.model?.modelType||null,variant:e.plan.info.runtime?.variant||null,useGpu:e.plan.info.runtime?.use_gpu||!1,durationMs:Date.now()-r,success:!0}),n}catch(t){throw U.addModelLoad({id:e.id,generatorId:e.id,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,modelType:e.plan.info.model?.modelType||null,variant:e.plan.info.runtime?.variant||null,durationMs:Date.now()-r,success:!1,error:t?.message||String(t)}),t}})();try{return await n.ready,typeof t==`function`&&t(1),n}catch(t){throw e.contextRecord=null,t}},$n=async(e,t,n=!1)=>t.released||!n&&t.refCount>0?!1:(t.released=!0,e.contextRecord=null,await t.context?.release?.(),!0),er=async(e,t,n=!1)=>{if(t.releaseRequested=!0,t.releaseTimer&&=(clearTimeout(t.releaseTimer),null),n)t.refCount=0;else if(t.refCount=Math.max(0,t.refCount-1),t.refCount>0)return t.releaseRequested=!1,!1;let r=e.config.runtime.context_release_delay_ms;if(typeof r!=`number`||!Number.isFinite(r))return $n(e,t);let i=Math.max(0,Math.floor(r));return n||i<=0?$n(e,t):(console.log(`[Context] Scheduling STT release in ${i}ms`),t.releaseTimer=setTimeout(async()=>{if(t.releaseTimer=null,t.refCount>0){console.log(`[Context] STT release cancelled, refCount=${t.refCount}`),t.releaseRequested=!1;return}console.log(`[Context] Releasing STT context after ${i}ms delay`),await $n(e,t)},i),!0)};async function tr(e,t,n={}){let{globalDownloadManager:r=null}=n,i=Nn(t),a=await Jn(i),o={id:e,type:`ggml-stt`,config:i,plan:a,info:a.info,contextRecord:null,downloads:new Map,globalDownloadManager:r,queue:new Xn,finalized:!1},s=async()=>{if(o.finalized)return;o.finalized=!0;let e=o.contextRecord;e&&(e.released||e.releaseRequested||e.releaseTimer||(e.refCount=Math.max(0,e.refCount-1),!(e.refCount>0)&&await $n(o,e)))},c=async(e={})=>{let{onProgress:t}=e;try{let e=await Qn(o,t);return{modelInfo:e.modelInfo&&typeof e.modelInfo==`object`?{...e.modelInfo}:null,runtime:{...o.plan.info.runtime},download:{...o.plan.info.download}}}catch(e){throw console.error(`[Context] Error initializing context:`,e),e}},u=async()=>{if(o.finalized)return!1;let e=o.contextRecord;return e?er(o,e):!1},d=async(e={})=>{let{audioPath:t,audioData:n,options:r={}}=e,i=o.contextRecord;if(!i)throw Error(`Context not initialized`);let a={...r};o.plan.info.runtime.max_threads&&a.maxThreads==null&&(a.maxThreads=o.plan.info.runtime.max_threads);let s=`transcription-${Date.now()}-${Math.random().toString(36).slice(2,8)}`,c=Date.now();return o.queue.enqueue(async()=>{await i.ready;try{let e;if(n){let t=Zn(n),{promise:r}=i.context.transcribeData(t,a);e=await r}else{if(!t)throw Error(`audioPath or audioData is required for transcription`);let n=l.resolve(t),{promise:r}=i.context.transcribe(n,a);e=await r}return U.addTranscription({id:s,generatorId:o.id,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,durationMs:Date.now()-c,segmentCount:e?.segments?.length||0,textLength:e?.text?.length||0,success:!0}),e}catch(e){throw U.addTranscription({id:s,generatorId:o.id,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,durationMs:Date.now()-c,success:!1,error:e?.message||String(e)}),e}},s)};return{id:e,type:`ggml-stt`,info:a.info,queue:o.queue,initContext:c,transcribe:async(e={})=>d(e),transcribeData:async(e={})=>d(e),releaseContext:u,finalize:s,getStatus:()=>({id:o.id,type:o.type,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,hasContext:!!o.contextRecord?.context,contextRefCount:o.contextRecord?.refCount||0,queueStatus:o.queue.getStatus()}),hasPendingReleases:()=>{let e=o.contextRecord;return e?!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0):!1},resetFinalized:()=>{o.finalized=!1}}}const nr=e=>{let t=Nn(e),n=t.model.repo_id||t.model.repository||t.model.model||null;if(!n)return null;let r=kn(t.model.filename);return r?`${n}:${r}`:n};async function rr(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n;try{let n=Nn(e),o=await Kn(n),s=Un(n,o),{repoId:c}=o;if(await Wn(s,o.size))return console.log(`[Download] STT model already exists: ${c} at ${s}`),typeof i==`function`&&i({localPath:s,repoId:c,alreadyExists:!0}),{started:!1,localPath:s,repoId:c,alreadyExists:!0};let l=t.getDownload(s);if(l)return console.log(`[Download] Already downloading STT model: ${c}`),l.then(()=>{typeof i==`function`&&i({localPath:s,repoId:c,joinedExisting:!0})}).catch(e=>{typeof a==`function`&&a(e)}),{started:!1,localPath:s,repoId:c,alreadyDownloading:!0};console.log(`[Download] Starting STT model download: ${c}`);let u=(async()=>{try{await Gn(o.url,o.headers,s,o.size,e=>{e>=0&&Number.isFinite(e)&&(console.log(`[Download] ${c}: ${Math.round(e*100)}%`),typeof r==`function`&&r(e))}),console.log(`[Download] Completed STT model: ${c}`),typeof i==`function`&&i({localPath:s,repoId:c})}catch(e){throw console.error(`[Download] Failed STT model: ${c}`,e.message),typeof a==`function`&&a(e),e}finally{t.deleteDownload(s)}})();return t.setDownload(s,u),{started:!0,localPath:s,repoId:c}}catch(e){return console.error(`[Download] Failed to start STT download:`,e.message),typeof a==`function`&&a(e),{started:!1,localPath:null,repoId:null,error:e.message}}}const ir=e=>e?typeof e.score==`number`&&Number.isFinite(e.score)?Number(e.score):ue(e):0;async function ar(e=null,t={}){let{threshold:n=1.1,includeBreakdown:r=!1,config:i,...a}=t,o=null,s=null,c=null;if(i)try{let e=await Kn(Nn(i));o=e.size??null,{processingBufferBytes:s}=Ne({modelBytes:o}),c=e.quantization||null}catch{}let l=i?.backend?.gpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.gpu_memory_fraction))),u=i?.backend?.cpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.cpu_memory_fraction))),d=await ke({...a,platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-stt`,includeBreakdown:r,gpuMemoryFraction:l,cpuMemoryFraction:u,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:o,kvCacheBytes:s}),f=d.selected,p=ir(f);f&&(f.modelBytes=o||null,f.processingBytes=s||null,f.quantization=c||null);let m=null,h=null;if(e){let t=ir(e);h={...e,score:t};let r=`buttress`,i=`buttress-higher-score`;if(!d.ok)r=`local`,i=`buttress-unavailable`;else if(!t&&t!==0)r=`buttress`,i=`missing-client-score`;else if(e.fit&&f?.fit){let a=e.fit.fitsInGpu||e.fit.fitsInCpu,o=f.fit.fitsInGpu||f.fit.fitsInCpu;a&&!o?(r=`local`,i=`client-fits-in-memory`):o&&!a?(r=`buttress`,i=`buttress-fits-in-memory`):t>p*n?(r=`local`,i=`client-better`):p>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`)}else t>p*n?(r=`local`,i=`client-better`):p>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`);m={buttressScore:p,clientScore:t,threshold:n,recommendation:r,reason:i}}!d.ok&&!m&&(m={buttressScore:p,clientScore:e?.score??null,threshold:n,recommendation:`local`,reason:`buttress-unavailable`});let g=null;return i&&(g={repoId:i.model?.repo_id||null,quantization:i.model?.quantization||null,filename:i.model?.filename||null}),{type:`ggml-stt`,timestamp:new Date().toISOString(),buttress:d,client:h,comparison:m,modelConfig:g}}const{ReadableStream:or}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,sr=te(import.meta.url),cr=l.dirname(sr),lr=l.join(cr,`mlx-bridge.py`),ur=`mlx-vlm==0.4.0`,dr=`mlx-lm==0.31.1`,fr=l.join(x.homedir(),`.buttress`,`models`),pr={backend:{type:`mlx-llm`},model:{repo_id:null,revision:`main`,adapter_path:null,tokenizer_config:null,model_config:null,vlm:`auto`},runtime:{cache_dir:fr,huggingface_token:process.env.HUGGINGFACE_TOKEN||null,mlx_env_dir:null,mlx_lm_package:dr,mlx_vlm_package:ur,context_release_delay_ms:1e4,session_cache:{enabled:!0,max_size_bytes:5*1024*1024*1024,max_entries:100}}},mr=(e,t)=>e==null?t:typeof e==`number`?e:typeof e==`string`?E.parse(e)??t:t,hr=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),hr(e[t],n)):e[t]=n}),e),gr=(e={})=>{let t=structuredClone(pr);return hr(t,e),t},_r=async(e,t={})=>{let n=await fetch(e,t);if(!n.ok)throw Error(`HTTP ${n.status}: ${e}`);return n.json()},vr=async e=>{await p(e,{recursive:!0})},yr=(e,t,n)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(n,`.metadata-cache`,t,`${r}.json`)},br=async(e,t,n)=>{try{let r=await h(yr(e,t,n),`utf-8`);return JSON.parse(r)}catch{return null}},xr=async(e,t,n,r)=>{try{let i=yr(e,t,r);await vr(l.dirname(i)),await b(i,JSON.stringify(n),`utf-8`)}catch{}};async function Sr(e,{revision:t=`main`,cacheDir:n,token:r}={}){let i=JSON.stringify({repoId:e,revision:t,type:`mlx-model-metadata`});if(n){let e=await br(i,`mlx-model-metadata`,n);if(e)return e}let a={};r&&(a.Authorization=`Bearer ${r}`);let o=(await _r(`https://huggingface.co/api/models/${e}?revision=${t}&blobs=true`,{headers:a}))?.siblings||[],s=0;for(let e of o){let t=e.rfilename||e.path||e.filename||``;/\.(safetensors|npz)$/.test(t)&&(s+=Number(e.size)||0)}let c=null;try{c=await _r(`https://huggingface.co/${e}/raw/${t}/config.json`,{headers:a})}catch{}let l=c?.text_config||c||{},u=c||{},d=u.model_type||u.architectures?.[0]||null,f=l.hidden_size||l.dim||0,p=l.num_hidden_layers||l.n_layers||0,m=l.num_attention_heads||l.n_heads||0,h=l.num_key_value_heads??m,g=l.vocab_size||0,_=l.max_position_embeddings||0,v=l.intermediate_size||0,y=l.head_dim||l.v_head_dim||(m>0&&f>0&&Number.isInteger(f/m)?f/m:0),b=l.kv_lora_rank||0,x=l.qk_rope_head_dim||0,S=b>0,C=u.quantization||u.quantization_config||null,w=C?.bits||null,T=C?.group_size||null,E=l.dtype||u.torch_dtype||(w?`${w}bit`:null),D={repoId:e,revision:t,modelBytes:s,arch:d,hiddenSize:f,numLayers:p,numHeads:m,numKvHeads:h,headDim:y,vocabSize:g,maxCtx:_,intermediateSize:v,quantBits:w,quantGroupSize:T,dtype:E,isMLA:S,kvLoraRank:b,qkRopeHeadDim:x,fileCount:o.length,config:c};return n&&await xr(i,`mlx-model-metadata`,D,n),D}function Cr({numLayers:e,numKvHeads:t,headDim:n,contextLength:r,isMLA:i,kvLoraRank:a,qkRopeHeadDim:o}){return!e||!r?0:i&&a>0?e*(a+(o||0))*r*2:!t||!n?0:e*t*n*r*2*2}const wr=async e=>{try{return await v(e),!0}catch{return!1}},q=(e,t,n={})=>new Promise((r,i)=>{ne(e,t,{timeout:n.timeout||3e5,...n},(t,n,a)=>{if(t){let n=a?.toString().trim()||t.message;i(Error(`${e} failed: ${n}`))}else r({stdout:n?.toString()||``,stderr:a?.toString()||``})})}),Tr=new Map;async function Er({envDir:e,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r}){let i=l.resolve(e),a=Tr.get(i);if(a){let e=await a;return r?.(1),e}let o=Or({envDir:i,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r});Tr.set(i,o);try{return await o}finally{Tr.delete(i)}}const Dr=[3,10];async function Or({envDir:e,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r}){let i=l.join(e,`bin`,`python3`),a=l.join(e,`bin`,`pip`);if(await wr(i))try{return await q(i,[`-c`,`import mlx_vlm; import torch`],{timeout:1e4}),r?.(1),i}catch{}if(!await wr(i)){r?.(.1);try{let{stdout:e}=await q(`python3`,[`-c`,`import sys; print(f"{sys.version_info.major}.{sys.version_info.minor}")`],{timeout:5e3}),[t,n]=e.trim().split(`.`).map(Number);(t<Dr[0]||t===Dr[0]&&n<Dr[1])&&console.warn(`[mlx-llm] WARNING: System Python is ${t}.${n}, but mlx-vlm requires >= ${Dr.join(`.`)}. You may get an older mlx-vlm version with reduced functionality. Consider installing Python >= 3.10 (e.g. via Homebrew).`)}catch{}console.log(`[mlx-llm] Creating venv at ${e}`),await p(e,{recursive:!0}),await q(`python3`,[`-m`,`venv`,e],{timeout:6e4}),r?.(.3)}return console.log(`[mlx-llm] Installing ${n}`),r?.(.4),await q(a,[`install`,t,n,`torch`,`torchvision`],{timeout:6e5,env:{...process.env}}),r?.(.9),await q(i,[`-c`,`import mlx_vlm; import torch; print(mlx_vlm.__version__)`],{timeout:15e3}),r?.(1),console.log(`[mlx-llm] mlx-vlm installed successfully`),i}var kr=class{constructor(){this.process=null,this.pendingRequests=new Map,this.requestCounter=0,this.readyPromise=null,this.buffer=``}spawn(e){return this.process=re(e,[lr],{stdio:[`pipe`,`pipe`,`pipe`],env:{...process.env,PYTHONUNBUFFERED:`1`}}),this.process.stderr.on(`data`,e=>{let t=e.toString().trim();t&&console.log(t)}),this.process.on(`exit`,e=>{console.log(`[mlx-llm] Bridge process exited with code ${e}`);for(let[t,n]of this.pendingRequests)n.reject(Error(`Bridge process exited (code ${e})`)),this.pendingRequests.delete(t);this.process=null}),this.process.stdout.on(`data`,e=>{this.buffer+=e.toString();let t=this.buffer.split(`
+import{t as e}from"./chunk-C8PTHxhX.mjs";import{node as t}from"@elysiajs/node";import{Elysia as n,file as r,sse as i,t as a}from"elysia";import o,{createHash as s,randomUUID as c}from"node:crypto";import l from"node:path";import*as u from"node:stream/web";import{ReadableStream as d}from"node:stream/web";import f,{mkdir as p,open as m,readFile as h,readdir as g,rename as _,stat as v,unlink as y,writeFile as b}from"node:fs/promises";import x from"node:os";import{gguf as S}from"@huggingface/gguf";import{getBackendDevicesInfo as C,isLibVariantAvailable as w,loadModel as T}from"@fugood/llama.node";import E from"bytes";import{EventEmitter as D}from"node:events";import{initWhisper as ee}from"@fugood/whisper.node";import{fileURLToPath as te}from"node:url";import{execFile as ne,execSync as O,spawn as re}from"node:child_process";import k from"node:fs";import A from"@iarna/toml";import{ZodError as j,z as M}from"zod";import{importSPKI as N,jwtVerify as P}from"jose";import{cors as ie}from"@elysiajs/cors";import F from"node-machine-id";import I from"ms";import{Buffer as L}from"node:buffer";import R from"node:dgram";const z=1024**3,ae=(e,t,n)=>Math.min(Math.max(e,t),n),oe=e=>e?40:0,se=(e=0)=>e?ae(e/(12*z)*20,0,20):0,ce=(e=0)=>e?ae(e/(32*z)*10,0,10):0,le=e=>e?10:0,B=(e=`default`,t=null)=>{let n=String(e).toLowerCase();return n?n.includes(`cuda`)?20:n.includes(`vulkan`)?10:n.includes(`default`)?t===`darwin`||t===`ios`?15:5:0:0},ue=({platform:e,variant:t,hasGpu:n,gpuUsableBytes:r=0,cpuUsableBytes:i=0,ok:a=!0}={})=>{if(!a)return 0;let o=oe(n)+B(t,e)+se(r),s=ce(i),c=le(a);return Math.min(100,Math.round(o+s+c))},de=({platform:e,variant:t,hasGpu:n,gpuUsableBytes:r=0,cpuUsableBytes:i=0,ok:a=!0}={})=>({gpuPresence:oe(n),variant:B(t,e),gpuMemory:se(r),cpuMemory:ce(i),availability:le(a)}),fe=[`cuda`,`vulkan`,`snapdragon`,`default`],pe=.85,me=.5,he=e=>!e&&e!==0?[]:Array.isArray(e)?e.filter(e=>e!=null):[e],ge=e=>e&&String(e).trim().toLowerCase()||null,_e=({variant:e,preferVariants:t=[],variantPreference:n=[],defaultVariants:r=fe}={})=>{let i=[];e&&i.push(e),i.push(...he(t)),i.push(...he(n)),i.push(...r);let a=new Set;for(let e of i){let t=ge(e);t&&a.add(t)}return Array.from(a)},ve=(e={})=>{let t=String(e.type||e.deviceType||e.kind||``).toLowerCase();return!!(t.includes(`gpu`)||t.includes(`cuda`)||t.includes(`metal`)||t.includes(`vulkan`)||t.includes(`snapdragon`))},ye=e=>Array.isArray(e)?e.map(e=>({...e})):[],be=(e,t)=>e===`snapdragon`?t.filter(e=>e.deviceName!==`GPUOpenCL`):t,xe=({platform:e,totalMemoryInBytes:t,variant:n,devices:r,gpuMemoryFraction:i,cpuMemoryFraction:a,ok:o,error:s})=>{let c=ye(be(n,r)),l=c.some(ve),u=c.filter(e=>ve(e)&&Number.isFinite(Number(e.maxMemorySize))).reduce((e,t)=>e+t.maxMemorySize,0),d=t,f=l?Math.floor(u*i):0,p=d?Math.floor(d*a):0,m={platform:e,variant:n,hasGpu:l,gpuUsableBytes:f,cpuUsableBytes:p,ok:o};return{platform:e,ok:o,variant:n,hasGpu:l,devices:c,gpuTotalBytes:u,gpuUsableBytes:f,cpuTotalBytes:d,cpuUsableBytes:p,score:ue(m),breakdown:o?de(m):null,error:s,timestamp:new Date().toISOString()}},Se=({device:e,modelBytes:t=0,kvCacheBytes:n=0}={})=>{if(!e)return{totalRequiredBytes:t+n,fitsInGpu:!1,fitsInCpu:!1,limiting:`unknown-device`};let r=Math.max(0,Number(t)||0)+Math.max(0,Number(n)||0),i=e.hasGpu&&r>0&&r<=e.gpuUsableBytes,a=r>0&&r<=e.cpuUsableBytes,o=`ok`;return!i&&e.hasGpu&&(o=`gpu-memory`),a||(o=i?`cpu-memory`:`insufficient-memory`),{totalRequiredBytes:r,fitsInGpu:i,fitsInCpu:a,limiting:o}},Ce=async({platform:e,variant:t=null,preferVariants:n=[],variantPreference:r=[],gpuMemoryFraction:i=pe,cpuMemoryFraction:a=me,includeBreakdown:o=!1,totalMemoryInBytes:s,modelBytes:c=null,kvCacheBytes:l=null,limitedKvCacheBytes:u=null,dependencies:d={},defaultVariants:f=fe}={})=>{let{getBackendDevicesInfo:p,isLibVariantAvailable:m}=d;if(typeof p!=`function`||typeof m!=`function`)throw TypeError(`GGML capability detection requires getBackendDevicesInfo and isLibVariantAvailable functions`);let h=_e({variant:t,preferVariants:n,variantPreference:r,defaultVariants:f}),g=[];for(let t of h)try{if(!await m(t))throw Error(`Variant ${t} not available on this platform`);let n=await p(t);g.push(xe({platform:e,totalMemoryInBytes:s,variant:t,devices:n,gpuMemoryFraction:i,cpuMemoryFraction:a,ok:!0}))}catch(n){let r=n instanceof Error?n.message:String(n);g.push(xe({platform:e,totalMemoryInBytes:s,variant:t,devices:[],gpuMemoryFraction:i,cpuMemoryFraction:a,ok:!1,error:r}))}let _=g.filter(e=>e.ok)[0]||null,v={ok:!!_,selected:_?{..._,breakdown:o?_.breakdown:void 0}:null,attempts:g};if(!o&&v.selected&&delete v.selected.breakdown,!v||!c&&!l)return v;let y=e=>{if(!e)return e;let t=Se({device:e,modelBytes:c||0,kvCacheBytes:l||0}),n=null;return u!=null&&u!==l&&(n=Se({device:e,modelBytes:c||0,kvCacheBytes:u})),{...e,fit:t,...n&&{limitedFit:n}}};return v.selected=y(v.selected),v.attempts=Array.isArray(v.attempts)?v.attempts.map(y):v.attempts,v},we=`ggml-llm`,Te=[`cuda`,`vulkan`,`default`],Ee=async({platform:e,variant:t=null,preferVariants:n=[],variantPreference:r=[],gpuMemoryFraction:i=pe,cpuMemoryFraction:a=me,includeBreakdown:o=!1,totalMemoryInBytes:s,modelBytes:c=null,processingBytes:l=null,kvCacheBytes:u=null,dependencies:d={}}={})=>Ce({platform:e,variant:t,preferVariants:n,variantPreference:r&&r.length>0?r:Te,gpuMemoryFraction:i,cpuMemoryFraction:a,includeBreakdown:o,totalMemoryInBytes:s,modelBytes:c,kvCacheBytes:l??u,dependencies:d,defaultVariants:Te}),De=async({platform:e,arch:t=null,unifiedMemoryFraction:n=.85,includeBreakdown:r=!1,totalMemoryInBytes:i,modelBytes:a=null,kvCacheBytes:o=null,limitedKvCacheBytes:s=null}={})=>{let c=[];e!==`darwin`&&c.push(`MLX requires macOS`),t&&t!==`arm64`&&c.push(`MLX requires Apple Silicon (arm64)`);let l=c.length===0,u=l?Math.floor(i*n):0,d={platform:e,variant:`mlx`,hasGpu:l,gpuUsableBytes:u,cpuUsableBytes:u,ok:l},f=ue(d),p=l?de(d):null,m={platform:e,ok:l,variant:`mlx`,hasGpu:l,unifiedMemory:!0,devices:l?[{type:`metal`,deviceName:`Apple Silicon (Unified Memory)`,maxMemorySize:i}]:[],gpuTotalBytes:l?i:0,gpuUsableBytes:u,cpuTotalBytes:i,cpuUsableBytes:u,score:f,breakdown:r?p:void 0,error:l?void 0:c.join(`; `),timestamp:new Date().toISOString()};r||delete m.breakdown;let h={ok:l,selected:l?m:null,attempts:[m],errors:l?[]:c};if(!a&&!o)return h;let g=e=>{if(!e)return e;let t=Se({device:e,modelBytes:a||0,kvCacheBytes:o||0}),n=null;return s!=null&&s!==o&&(n=Se({device:e,modelBytes:a||0,kvCacheBytes:s})),{...e,fit:t,...n&&{limitedFit:n}}};return h.selected=g(h.selected),h.attempts=h.attempts.map(g),h},Oe=new Map([[we,Ce],[`ggml-stt`,Ee],[`mlx-llm`,De]]),ke=async({platform:e,totalMemoryInBytes:t,backend:n=we,dependencies:r,...i}={})=>{let a=Oe.get(n);if(!a)throw Error(`No capability detector registered for backend "${n}"`);return await a({...i,dependencies:r,totalMemoryInBytes:t,platform:e})},Ae={f16:2,f32:4,q8_0:1,q6_k:.75,q5_k:.625,q5_k_m:.625,q5_k_s:.625,q5_1:.625,q5_0:.625,q4_k:.5,q4_k_m:.5,q4_k_s:.5,q4_1:.5,q4_0:.5,iq4_nl:.5},je=e=>Ae[e?String(e).toLowerCase():`f16`]||Ae.f16,Me=(e,t,n,r,i,a={},{totalLayers:o=null,swaLayers:s=0,swaContext:c=null,swaContextMultiplier:l=1,swaAdditionalTokens:u=0,swaFull:d=!1}={})=>{if(!e||!t||!n||!r||!i)return 0;let f=o!=null&&o!==void 0?Number(o):Number(e),p=Math.max(0,Math.floor(f));if(!p)return 0;let m=je(a.k),h=je(a.v),g=Number(n)*(Number(r)*m+Number(i)*h);if(!g)return 0;let _=Math.max(0,Number(t)||0),v=Math.min(p,Math.max(0,Math.floor(Number(s)||0))),y=Math.max(0,p-v),b=c!=null&&Number.isFinite(Number(c))?Math.max(0,Number(c)):_,x=Math.max(1,Number(l)||1),S=Math.max(0,Number(u)||0),C=b*x+S,w=d?_:Math.min(_,C),T=y*_+v*Math.max(0,Math.floor(w));return Math.round(g*T)},Ne=({modelBytes:e=0,audioLengthSeconds:t=30,sampleRate:n=16e3,bytesPerSample:r=4}={})=>{let i=Math.max(0,Number(e)||0),a=Math.max(0,Math.floor(Math.max(0,t)*n*r)),o=1024*1024,s=1024*o,c;c=i<200*o?120*o:i<500*o?140*o:i<2*s?150*o:160*o;let l;l=i<200*o?70*o:i<500*o?135*o:(2*s,220*o);let u;u=i<100*o?20*o:i<200*o?30*o:i<500*o?85*o:i<2*s?215*o:360*o;let d=c+l+u;return{modelBytes:i,audioBufferBytes:a,processingBufferBytes:d,totalBytes:i+d+a}},Pe=e=>e?String(e).trim().toLowerCase():null,Fe=(e={},t=null)=>{if(!e)return null;let n=Pe(t),r=n?`${n}.attention.sliding_window`:null,i=(r&&e[r]!=null?e[r]:null)??e[`llama.attention.sliding_window`];if(i==null)return null;let a=Number(i);return Number.isFinite(a)?a:null},Ie=(e=0,t=0,n=!1)=>{let r=Math.max(0,Math.floor(Number(e)||0)),i=Math.max(0,Math.floor(Number(t)||0));if(!r||i===1)return 0;if(i<=0)return r;let a=Math.max(0,i-1),o=Math.floor(r/i),s=r%i,c=n?Math.max(0,s-1):Math.min(s,a);return o*a+c},Le=({arch:e,nLayer:t=0})=>({arch:Pe(e),enabled:!1,window:null,pattern:null,denseFirst:!1,type:null,kvLayers:Math.max(0,Math.floor(Number(t)||0)),swaLayers:0}),Re=new Map([[`llama4`,({nSwa:e})=>e===0?{enabled:!1}:{enabled:!0,window:e&&e>0?e:8192,pattern:4,type:`chunked`}],[`afmoe`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`phi3`,()=>({enabled:!1})],[`gemma2`,({nSwa:e})=>{let t=e&&e>0?e:4096;return t?{enabled:!0,window:t,pattern:2,type:`standard`}:{enabled:!1}}],[`gemma3`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:6,type:`standard`}],[`gemma3n`,({nLayer:e,nSwa:t})=>!t||t<=0?{enabled:!1}:{enabled:!0,window:t,pattern:5,type:`standard`,kvLayers:Math.min(20,e)}],[`gemma-embedding`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:6,type:`symmetric`}],[`cohere2`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`olmo2`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:4,type:`standard`}],[`exaone4`,({nLayer:e,nSwa:t})=>{let n=e>=64,r=null;return t&&t>0?r=t:n&&(r=4096),r?{enabled:!0,window:r,pattern:4,type:`standard`}:{enabled:!1}}],[`gpt-oss`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:e,pattern:2,type:`standard`}],[`gemma4`,({nLayer:e,nSwa:t,metadata:n})=>{if(!t||t<=0)return{enabled:!1};let r=Number(n?.[`gemma4.attention.shared_kv_layers`])||0,i=Math.max(0,e-r),a=n?.[`gemma4.attention.sliding_window_pattern`];return Array.isArray(a)?{enabled:!0,window:t,type:`standard`,swaLayers:a.slice(0,i).filter(e=>Number(e)>0).length,kvLayers:i}:{enabled:!0,window:t,pattern:6,type:`standard`,kvLayers:i}}],[`smallthinker`,({nSwa:e})=>!e||e<=0?{enabled:!1}:{enabled:!0,window:4096,pattern:4,denseFirst:!0,type:`standard`}]]),ze=({arch:e,metadata:t={},nLayer:n=0}={})=>{let r=Pe(e||t[`general.architecture`]),i=Math.max(0,Math.floor(Number(n)||0)),a=Fe(t,r),o=r?Re.get(r):null;if(!o)return Le({arch:r,nLayer:n});let s=o({nLayer:i,nSwa:a,metadata:t});if(!s||!s.enabled||!s.window||s.window<=0)return Le({arch:r,nLayer:n});let c=Math.max(0,Math.floor(Number(s.pattern)||0)),l=s.kvLayers!=null&&Number.isFinite(Number(s.kvLayers))?Number(s.kvLayers):i,u=Math.max(0,Math.floor(l)),d=s.swaLayers!=null&&Number.isFinite(Number(s.swaLayers))?Math.max(0,Math.floor(Number(s.swaLayers))):Ie(u,c,!!s.denseFirst);return{arch:r,enabled:d>0,window:s.window,pattern:c,denseFirst:!!s.denseFirst,type:s.type||`standard`,kvLayers:u,swaLayers:d}},Be=new Set([`mamba`,`mamba2`,`rwkv6`,`rwkv6qwen2`,`rwkv7`,`arwkv7`]),Ve=new Set([`jamba`,`falcon-h1`,`plamo2`,`granitehybrid`,`lfm2`,`lfm2moe`,`nemotron_h`,`nemotron_h_moe`,`qwen3next`]),He=e=>e?String(e).trim().toLowerCase():null,Ue=e=>{let t=He(e);return t?Be.has(t):!1},We=e=>{let t=He(e);return t?Ve.has(t):!1},Ge=e=>Ue(e)?`recurrent`:We(e)?`hybrid`:`transformer`,Ke=(e={})=>{let t=e[`general.architecture`],n=(t,n=null)=>{let r=e[t],i=Number(r);return Number.isFinite(i)?i:n},r=(t,n=null)=>{let r=e[t];if(Array.isArray(r))return r;let i=Number(r);return Number.isFinite(i)?i:n},i=t?n(`${t}.context_length`,n(`llama.context_length`)):null,a=t?n(`${t}.block_count`,n(`llama.block_count`)):null,o=t?n(`${t}.embedding_length`,n(`llama.embedding_length`)):null,s=t?n(`${t}.attention.head_count`,n(`llama.attention.head_count`)):null,c=t?r(`${t}.attention.head_count_kv`,r(`llama.attention.head_count_kv`,s)):null,l=null,u=null;if(Array.isArray(c)){let e=c.filter(e=>Number(e)>0);e.length>0?(l=Math.max(...e.map(Number)),u=e.length):(l=0,u=0)}else l=c;let d=t?n(`${t}.attention.key_length`,n(`llama.attention.key_length`)):null,f=t?n(`${t}.attention.value_length`,n(`llama.attention.value_length`)):null,p=e[`general.quantization_version`]||null,m=e[`general.file_type`]||null,h=t?n(`${t}.ssm.conv_kernel`):null,g=t?n(`${t}.ssm.state_size`):null,_=t?n(`${t}.ssm.inner_size`):null,v=t?n(`${t}.ssm.group_count`):null,y=t?n(`${t}.ssm.time_step_rank`):null,b=t?n(`${t}.rwkv.head_size`):null,x=t?n(`${t}.rwkv.token_shift_count`,2):null,S=t?n(`${t}.attention.shared_kv_layers`,0):0,C=u!=null&&a!=null?a-u:null;return{arch:t,nCtxTrain:i,nLayer:a,nEmbd:o,nHead:s,nHeadKv:l,nEmbdHeadK:d,nEmbdHeadV:f,quantVersion:p,fileType:m,attentionLayerCount:u,recurrentLayerCount:C,ssmDConv:h,ssmDState:g,ssmDInner:_,ssmNGroup:v,ssmDtRank:y,rwkvHeadSize:b,rwkvTokenShiftCount:x,sharedKvLayers:S}},qe=({layerCount:e,headKvCount:t,embdHeadKCount:n,embdHeadVCount:r,cacheTypes:i,swaConfig:a,kvUnified:o=!1,nParallel:s=1,swaFull:c=!1,arch:l=null,attentionLayerCount:u=null})=>{let d=Ge(l);if(d===`recurrent`)return()=>0;let f=d===`hybrid`&&u!=null?Math.max(0,Math.floor(Number(u)||0)):e,p=a?.window&&o?Math.max(1,Number(s)||1):1,m=o?1:Math.max(1,Number(s)||1);return e=>Me(f,e,t,n,r,i,{totalLayers:f,swaLayers:a?.swaLayers||0,swaContext:a?.window,swaFull:c,swaContextMultiplier:p})*m},Je=({nLayer:e,nEmbd:t,recurrentLayerCount:n=null,nSeqMax:r=1,ssmDConv:i=null,ssmDState:a=null,ssmDInner:o=null,ssmNGroup:s=null,ssmDtRank:c=null,rwkvHeadSize:l=null,rwkvTokenShiftCount:u=2,arch:d=null})=>{if(Ge(d)===`transformer`)return 0;let f=n==null?Math.max(0,Math.floor(Number(e)||0)):Math.max(0,Math.floor(Number(n)||0));if(f===0)return 0;let p=Math.max(1,Math.floor(Number(r)||1)),m=0,h=0;if(l!=null&&l>0&&t!=null&&t>0)m=Math.max(1,Number(u)||2)*t,h=t*l;else if(a!=null&&o!=null){let e=Math.max(0,Number(i)||0),t=Math.max(0,Number(a)||0),n=Math.max(0,Number(o)||0),r=Math.max(1,Number(s)||1);Math.max(0,Number(c)||0)>0?(m=e>0?(e-1)*2*r*t:0,h=Math.floor(t*n/2)):(m=e>0?(e-1)*(n+2*r*t):0,h=t*n)}else return 0;let g=(m+h)*p*f*4;return Math.max(0,g)},Ye=({maxCtx:e,availableMemory:t,modelBytes:n,kvBytesForCtx:r})=>{let i=Math.max(1,Math.floor(Number(e)||0));if(!r||t<=n)return i;let a=1,o=i,s=i;for(;a<=o;){let e=Math.floor((a+o)/2);n+r(e)<=t?(s=e,a=e+1):o=e-1}return s},V=new D;V.setMaxListeners(100);const Xe=(e,t,n)=>{e.push({...t,timestamp:t.timestamp||new Date().toISOString()}),e.length>n&&e.shift()};var Ze=class{constructor(e=9999){this.maxEntries=e,this.modelLoads=[],this.completions=[],this.transcriptions=[]}addModelLoad(e){Xe(this.modelLoads,e,this.maxEntries),V.emit(`status:modelLoad`,e),V.emit(`status:change`,{type:`modelLoad`,entry:e})}addCompletion(e){Xe(this.completions,e,this.maxEntries),V.emit(`status:completion`,e),V.emit(`status:change`,{type:`completion`,entry:e})}addTranscription(e){Xe(this.transcriptions,e,this.maxEntries),V.emit(`status:transcription`,e),V.emit(`status:change`,{type:`transcription`,entry:e})}getModelLoadHistory(){return[...this.modelLoads].reverse()}getCompletionHistory(){return[...this.completions].reverse()}getTranscriptionHistory(){return[...this.transcriptions].reverse()}clear(){this.modelLoads=[],this.completions=[],this.transcriptions=[]}};const H=new Ze,U=new Ze;let Qe=0;function $e(e){let t=t=>e(t);return V.on(`status:change`,t),()=>V.off(`status:change`,t)}function et(e){return Qe+=1,{subscriberId:Qe,unsubscribe:$e(e)}}function tt(e){let t=[];return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`ggml-llm`).map(([e,n])=>{let{instance:r}=n,i=[];return r.contexts&&(i=Array.from(r.contexts.entries()).map(([n,r])=>{let i={key:n,refCount:r.refCount,hasModel:!!r.context},a=r.context.parallel.getStatus();return i.parallelStatus=a,t.push({generatorId:e,contextKey:n,...a}),i})),{id:e,type:n.type,refCount:n.refCount,repoId:r.info?.model?.repoId||null,quantization:r.info?.model?.quantization||null,variant:r.info?.runtime?.variant||null,nCtx:r.info?.runtime?.n_ctx||null,nParallel:r.info?.runtime?.n_parallel||null,contexts:i}}),parallelStatuses:t,history:{modelLoads:H.getModelLoadHistory().filter(e=>e.variant!==`mlx`),completions:H.getCompletionHistory().filter(e=>e.variant!==`mlx`)}}}function nt(e){return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`ggml-stt`).map(([e,t])=>{let{instance:n}=t,r=n.getStatus?.()||{},i=r.queueStatus||{processing:!1,queuedCount:0};return{id:e,type:t.type,refCount:t.refCount,repoId:n.info?.model?.repoId||null,quantization:n.info?.model?.quantization||null,modelType:n.info?.model?.modelType||null,variant:n.info?.runtime?.variant||null,hasContext:r.hasContext||!1,contextRefCount:r.contextRefCount||0,queueStatus:i}}),history:{modelLoads:U.getModelLoadHistory(),transcriptions:U.getTranscriptionHistory()}}}function rt(e){return{generators:Array.from(e.entries()).filter(([,e])=>e.type===`mlx-llm`).map(([e,t])=>{let{instance:n}=t,r=n.getStatus?.()||{};return{id:e,type:t.type,refCount:t.refCount,repoId:r.repoId||n.info?.model?.repoId||null,variant:r.variant||`mlx`,contexts:r.contexts||[]}}),history:{modelLoads:H.getModelLoadHistory().filter(e=>e.variant===`mlx`),completions:H.getCompletionHistory().filter(e=>e.variant===`mlx`)}}}function it(e){return{timestamp:new Date().toISOString(),ggmlLlm:tt(e),ggmlStt:nt(e),mlxLlm:rt(e)}}const{ReadableStream:at,WritableStream:ot}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,st=(e,t)=>Object.prototype.hasOwnProperty.call(e||{},t),ct=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),ct(e[t],n)):e[t]=n}),e),lt=`https://huggingface.co`,ut=`https://huggingface.co/api`,W=l.join(x.homedir(),`.buttress`,`models`),dt=[`mxfp4`,`q8_0`,`q6_k`,`q6`,`q5_k_m`,`q5_k_s`,`q5_k`,`q5_1`,`q5_0`,`q4_k_m`,`q4_k_s`,`q4_k`,`q4_1`,`q4_0`,`q3`,`q2`],ft=.5,pt=[`speculative`,`spec_type`,`spec_draft_n_max`,`spec_draft_n_min`,`spec_draft_p_min`,`spec_draft_p_split`],mt=(e,t)=>{if(!(t==null||t===``)){if(e===`spec_draft_n_max`||e===`spec_draft_n_min`){let e=Number(t);return Number.isFinite(e)?Math.max(0,Math.floor(e)):void 0}if(e===`spec_draft_p_min`||e===`spec_draft_p_split`){let e=Number(t);return Number.isFinite(e)?Math.max(0,e):void 0}return t}},ht=e=>{let t={};for(let n of pt){let r=mt(n,e.model[n]??e.runtime[n]);r!==void 0&&(t[n]=r)}return t},gt=(e={})=>{let t={};for(let n of pt){let r=mt(n,e[n]);r!==void 0&&(t[n]=r)}return t},_t=(e={},t={})=>{let n=e||{},r=gt(t);return!Object.keys(r).length||pt.some(e=>st(n,e))?n:{...r,...n}},vt={backend:{type:`ggml-llm`,variant:null,variant_preference:[`cuda`,`vulkan`,`snapdragon`,`default`],gpu_memory_fraction:.85,cpu_memory_fraction:ft},model:{repo_id:null,revision:`main`,filename:null,url:null,quantization:null,preferred_quantizations:[],n_ctx:null,n_gpu_layers:`auto`,allow_local_file:!1,local_path:null,api_base:ut,base_url:lt,enable_mtmd:!1,mmproj_filename:null,mmproj_url:null,mmproj_local_path:null,mmproj_use_gpu:null,mmproj_image_min_tokens:-1,mmproj_image_max_tokens:-1,speculative:null,spec_type:null,spec_draft_n_max:null,spec_draft_n_min:null,spec_draft_p_min:null,spec_draft_p_split:null},runtime:{cache_dir:W,prefer_variants:[],huggingface_token:process.env.HUGGINGFACE_TOKEN||null,http_headers:{},session_cache:{enabled:!0,max_size_bytes:10*1024*1024*1024,max_entries:1e3},context_release_delay_ms:1e4}},yt=(e,t=[])=>!e&&e!==0?[...t]:Array.isArray(e)?e.filter(e=>e!=null):[e],bt=e=>{if(!e)return null;let t=String(e).toLowerCase();return[`cuda`,`vulkan`,`snapdragon`,`default`].includes(t)?t:null},xt=(e={})=>{let t=structuredClone(vt);if(ct(t,e),t.backend.variant=bt(t.backend.variant),t.backend.variant_preference=Array.from(new Set(yt(t.backend.variant_preference).flatMap(e=>{let t=bt(e);return t?[t]:[]}))),t.backend.variant_preference.length===0&&(t.backend.variant_preference=[`cuda`,`vulkan`,`snapdragon`,`default`]),t.runtime.prefer_variants=Array.from(new Set(yt(t.runtime.prefer_variants).flatMap(e=>{let t=bt(e);return t?[t]:[]}))),t.model.preferred_quantizations=Array.from(new Set(yt(t.model.preferred_quantizations||t.model.quantizations).map(e=>e?String(e).toLowerCase():null).filter(Boolean))),t.model.quantization){let e=String(t.model.quantization).toLowerCase();t.model.preferred_quantizations.includes(e)||t.model.preferred_quantizations.unshift(e)}t.model.n_parallel=t.model.n_parallel?Math.max(1,Number(t.model.n_parallel)):void 0,t.model.n_batch=Math.max(1,Number(t.model.n_batch)||512),t.model.base_url=t.model.base_url||lt,t.model.api_base=t.model.api_base||ut,t.model.enable_mtmd=!!t.model.enable_mtmd;let n=e=>{if(e==null)return-1;let t=Number(e);return Number.isFinite(t)?Math.floor(t):-1};return t.model.mmproj_image_min_tokens=n(t.model.mmproj_image_min_tokens),t.model.mmproj_image_max_tokens=n(t.model.mmproj_image_max_tokens),t.runtime.cache_dir=t.runtime.cache_dir?l.resolve(t.runtime.cache_dir):W,t.runtime.session_cache={...vt.runtime.session_cache,...t.runtime.session_cache||{}},t.runtime.context_release_delay_ms=Math.max(0,Number(t.runtime.context_release_delay_ms)||vt.runtime.context_release_delay_ms),t},St=e=>{let t=e.toLowerCase();return dt.find(e=>t.includes(e))||null},Ct=e=>{let t=[];return e.backend.variant&&t.push(e.backend.variant),e.runtime.prefer_variants.length>0&&t.push(...e.runtime.prefer_variants),t.push(...e.backend.variant_preference),t.push(`default`),Array.from(new Set(t.flatMap(e=>{let t=bt(e);return t?[t]:[]})))},G=async e=>{await p(e,{recursive:!0})},wt=(e=W)=>l.join(e,`.metadata-cache`),Tt=(e,t,n=W)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(wt(n),t,`${r}.json`)},Et=async(e,t,n=W)=>{try{let r=Tt(e,t,n),i=await h(r,`utf-8`);return console.log(`[Cache] Hit ${t} cache:`,l.basename(r)),JSON.parse(i,(e,t)=>typeof t==`string`&&t.startsWith(`__bigint__`)?BigInt(t.slice(10)):t)}catch{return null}},Dt=async(e,t,n,r=W)=>{try{let i=Tt(e,t,r);await G(l.dirname(i)),await b(i,JSON.stringify(n,(e,t)=>typeof t==`bigint`?`__bigint__${t.toString()}`:t),`utf-8`),console.log(`[Cache] Wrote ${t} cache:`,l.basename(i))}catch(e){console.warn(`[Cache] Failed to write ${t} cache:`,e.message)}},Ot=(e=W)=>l.join(e,`.session-state-cache`),kt=(e=W)=>l.join(Ot(e),`cache-map.json`),At=(e=W)=>l.join(Ot(e),`temp`),jt=(e=W)=>l.join(Ot(e),`states`),Mt=()=>({version:1,entries:{},totalSize:0}),Nt=async(e=W)=>{try{let t=await h(kt(e),`utf-8`),n=JSON.parse(t);return!n.entries||typeof n.entries!=`object`?Mt():n}catch{return Mt()}},Pt=async(e,t=W)=>{let n=kt(t),r=`${n}.tmp.${Date.now()}`;try{await G(l.dirname(n)),await b(r,JSON.stringify(e,null,2),`utf-8`),await _(r,n)}catch(e){throw await y(r).catch(()=>{}),e}},Ft=(e,t)=>{let n=JSON.stringify({text:e,model:t.modelPath,variant:t.variant,n_gpu_layers:t.n_gpu_layers,n_ctx:t.n_ctx,cacheTypeK:t.cacheTypeK,cacheTypeV:t.cacheTypeV,kvUnified:t.kvUnified,swaFull:t.swaFull,flashAttnType:t.flashAttnType});return s(`sha256`).update(n).digest(`hex`).slice(0,24)},It=(e,t=W)=>l.join(jt(t),`${e}.bin`),Lt=(e=W)=>{let t=`${Date.now()}-${Math.random().toString(36).slice(2,10)}`;return l.join(At(e),`${t}.bin`)},Rt=(e,t)=>e.modelPath===t.modelPath&&e.variant===t.variant&&e.n_gpu_layers===t.n_gpu_layers&&e.n_ctx>=t.n_ctx&&e.cacheTypeK===t.cacheTypeK&&e.cacheTypeV===t.cacheTypeV&&e.kvUnified===t.kvUnified&&e.swaFull===t.swaFull&&e.flashAttnType===t.flashAttnType&&!!e.isRecurrent==!!t.isRecurrent&&!!e.isHybrid==!!t.isHybrid,zt=(e,t)=>{let n=Math.min(e.length,t.length),r=0;for(;r<n&&e[r]===t[r];)r+=1;return r},Bt=(e,t,n,r=!1)=>{let i=Object.values(n.entries);console.log(`[SessionCache] Finding match for promptText (${e.length} chars), exactMatch=${r}`),console.log(`[SessionCache] Checking ${i.length} cache entries`);let a=i.filter(e=>Rt(e.metadata,t));if(r){let t=a.find(t=>t.fullText===e);return t?(console.log(`[SessionCache] Exact match found: ${t.id} (${t.fullText.length} chars)`),{entry:t,prefixLength:t.fullText.length,exactMatch:!0}):null}let o=a.reduce((t,n)=>{let r=zt(e,n.fullText);return r>t.prefixLen||r===t.prefixLen&&n.fullText.length>(t.entry?.fullText?.length||0)?{entry:n,prefixLen:r}:t},{entry:null,prefixLen:0});return o.entry?(console.log(`[SessionCache] Prefix match found: ${o.entry.id} (${o.prefixLen}/${o.entry.fullText.length} chars)`),{entry:o.entry,prefixLength:o.prefixLen}):(console.log(`[SessionCache] No match found`),null)},Vt=async(e,t,n)=>{let r=Object.values(e.entries),i=r.sort((e,t)=>new Date(e.lastAccessedAt)-new Date(t.lastAccessedAt)),a=e.totalSize,o=r.length,s=i.filter(e=>!(a>t)&&!(o>n)?!1:(a-=(e.stateFileSize||0)+(e.promptStateSize||0),--o,!0));return await Promise.all(s.map(async t=>{await y(t.stateFilePath).catch(()=>{}),t.promptStatePath&&await y(t.promptStatePath).catch(()=>{}),delete e.entries[t.id],console.log(`[SessionCache] Evicted entry: ${t.id}`)})),e.totalSize=Math.max(0,a),s.map(e=>e.id)},Ht=async(e,t,n,r)=>{let i=[];for(let[a,o]of Object.entries(e.entries))a!==n&&Rt(o.metadata,r)&&t.startsWith(o.fullText)&&o.fullText.length<t.length&&i.push(o);return await Promise.all(i.map(async t=>{await y(t.stateFilePath).catch(()=>{}),t.promptStatePath&&await y(t.promptStatePath).catch(()=>{}),e.totalSize-=(t.stateFileSize||0)+(t.promptStateSize||0),delete e.entries[t.id],console.log(`[SessionCache] Evicted superseded prefix entry: ${t.id} (${t.promptText.length} prompt chars)`)})),i.map(e=>e.id)},Ut=async(e=W)=>{let t=At(e);try{let e=await g(t),n=Date.now();await Promise.all(e.map(async e=>{let r=l.join(t,e),i=await v(r).catch(()=>null);i&&n-i.mtimeMs>36e5&&(await y(r).catch(()=>{}),console.log(`[SessionCache] Cleaned up temp file: ${e}`))}))}catch{}},Wt=async e=>{try{return await v(e),!0}catch{return!1}},Gt=(e,t)=>e==null?t:typeof e==`number`?e:typeof e==`string`?E.parse(e)??t:t;var Kt=class e{constructor(e,t){this.config=e,this.plan=t,this.baseDir=e.runtime.cache_dir,this.enabled=e.runtime.session_cache?.enabled!==!1,this.maxSizeBytes=Gt(e.runtime.session_cache?.max_size_bytes,10*1024*1024*1024),this.maxEntries=e.runtime.session_cache?.max_entries||1e3,this.metadata={variant:t.info?.runtime?.variant||null,n_gpu_layers:t.info?.runtime?.n_gpu_layers||0,n_ctx:t.info?.runtime?.n_ctx||0,modelPath:t.localPath,cacheTypeK:t.info?.runtime?.cache_type_k||`f16`,cacheTypeV:t.info?.runtime?.cache_type_v||`f16`,kvUnified:t.info?.runtime?.kv_unified??null,swaFull:t.info?.runtime?.swa_full??null,flashAttnType:t.info?.runtime?.flash_attn_type||`off`,isRecurrent:!1,isHybrid:!1},this.cacheMap=null,this.initialized=!1}updateModelInfo(e){e&&(this.metadata.isRecurrent=!!e.is_recurrent,this.metadata.isHybrid=!!e.is_hybrid,(this.metadata.isRecurrent||this.metadata.isHybrid)&&console.log(`[SessionCache] Model architecture: recurrent=${this.metadata.isRecurrent}, hybrid=${this.metadata.isHybrid}`))}requiresExactMatch(){return this.metadata.isRecurrent||this.metadata.isHybrid}async persistCacheMap(){try{await Pt(this.cacheMap,this.baseDir)}catch(e){console.warn(`[SessionCache] Failed to persist cache map: ${e?.message||e}`)}}static checkTokenPrefixMatch(e,t){if(e.length>t.length)return!1;for(let n=0;n<e.length;n+=1)if(e[n]!==t[n])return!1;return!0}static async tokenizeToArray(e,t){let n=await e.tokenize(t);return Array.from(n?.tokens||[])}async findFormattedMatchForRecurrent(t,n,r){let i=await e.tokenizeToArray(r,n),a=t.map(async t=>{try{let n=await e.tokenizeToArray(r,t.fullText);if(e.checkTokenPrefixMatch(n,i))return{entry:t,usePromptState:!1,tokenCount:n.length};if(t.promptStatePath&&t.promptText){let n=await e.tokenizeToArray(r,t.promptText);if(e.checkTokenPrefixMatch(n,i))return{entry:t,usePromptState:!0,tokenCount:n.length}}return null}catch(e){return console.warn(`[SessionCache] Failed to check entry ${t.id}: ${e.message}`),null}}),o=(await Promise.all(a)).find(e=>e!==null);if(!o)return console.log(`[SessionCache] No token prefix match found for recurrent/hybrid model`),null;let{entry:s,usePromptState:c,tokenCount:l}=o;return console.log(`[SessionCache] Token prefix match: ${s.id} (${l} tokens, usePromptState=${c})`),await Wt(c?s.promptStatePath:s.stateFilePath)?(s.lastAccessedAt=new Date().toISOString(),await this.persistCacheMap(),{entry:s,usePromptState:c}):(await this.removeStaleEntry(s),null)}async initialize(){if(!(!this.enabled||this.initialized))try{await G(Ot(this.baseDir)),await G(At(this.baseDir)),await G(jt(this.baseDir)),this.cacheMap=await Nt(this.baseDir),this.initialized=!0,console.log(`[SessionCache] Initialized with ${Object.keys(this.cacheMap.entries).length} entries`)}catch(e){console.warn(`[SessionCache] Failed to initialize: ${e.message}`),this.enabled=!1}}async removeStaleEntry(e){console.log(`[SessionCache] Removing stale entry: ${e.id}`),e.stateFilePath&&await y(e.stateFilePath).catch(()=>{}),e.promptStatePath&&await y(e.promptStatePath).catch(()=>{}),delete this.cacheMap.entries[e.id],this.cacheMap.totalSize-=(e.stateFileSize||0)+(e.promptStateSize||0),await this.persistCacheMap()}async findMatchingEntry(e,t=null){if(!this.enabled||!this.cacheMap)return null;let n=this.requiresExactMatch();if(n&&t){let n=Object.values(this.cacheMap.entries).filter(e=>Rt(e.metadata,this.metadata)&&e.fullText);return this.findFormattedMatchForRecurrent(n,e,t)}let r=Bt(e,this.metadata,this.cacheMap,n);if(!r)return null;let{entry:i}=r;return await Wt(i.stateFilePath)?(i.lastAccessedAt=new Date().toISOString(),await this.persistCacheMap(),{entry:i,usePromptState:!1}):(await this.removeStaleEntry(i),null)}async prepareCompletionOptions(e,t,n=null){let r={options:e,cacheEntry:null,promptPrefix:null};if(!this.enabled)return r;let i=await this.findMatchingEntry(t,n);if(!i)return r;let{entry:a,usePromptState:o}=i,s=o?a.promptStatePath:a.stateFilePath,c=o?a.promptText:a.fullText;return console.log(`[SessionCache] Found matching entry: ${a.id} (${c.length} chars, usePromptState=${o})`),{options:{...e,load_state_path:s},cacheEntry:a,promptPrefix:c}}async saveCompletionState(e,t,n,r=0,i=null){if(!this.enabled)return null;let a=e+t,o=Ft(a,this.metadata),s=()=>{n&&y(n).catch(()=>{}),i&&y(i).catch(()=>{})};if(this.cacheMap.entries[o]){console.log(`[SessionCache] Entry already exists for prompt: ${o}, updating position`);let e=this.cacheMap.entries[o];return e.lastAccessedAt=new Date().toISOString(),delete this.cacheMap.entries[o],this.cacheMap.entries[o]=e,await this.persistCacheMap(),s(),e}let c=It(o,this.baseDir),u=i?It(`${o}-prompt`,this.baseDir):null;try{await G(l.dirname(c)),await _(n,c);let s=await v(c),d=0;if(i&&u)try{await _(i,u),d=(await v(u)).size,console.log(`[SessionCache] Saved prompt state: ${u}`)}catch(e){console.warn(`[SessionCache] Failed to save prompt state: ${e.message}`)}let f={id:o,promptText:e,completionText:t,fullText:a,promptTokenCount:r,stateFilePath:c,stateFileSize:s.size,promptStatePath:u||null,promptStateSize:d,metadata:{...this.metadata},createdAt:new Date().toISOString(),lastAccessedAt:new Date().toISOString()};return this.cacheMap.entries[o]=f,this.cacheMap.totalSize+=s.size+d,this.requiresExactMatch()||await Ht(this.cacheMap,e,o,this.metadata),await Vt(this.cacheMap,this.maxSizeBytes,this.maxEntries),await Pt(this.cacheMap,this.baseDir),console.log(`[SessionCache] Saved entry: ${o} (${s.size} bytes, ${a.length} chars)`),f}catch(e){return console.warn(`[SessionCache] Failed to save state: ${e.message}`),s(),null}}async generateTempStatePath(){return await G(At(this.baseDir)),Lt(this.baseDir)}async cleanup(){await Ut(this.baseDir)}};const qt=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,t);if(!n.ok){let t=await n.text().catch(()=>``);throw Error(`Failed to fetch ${e}: ${n.status} ${n.statusText} ${t}`.trim())}return n.json()},Jt=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,{...t,method:`HEAD`});if(!n.ok)throw Error(`Failed to fetch headers for ${e}: ${n.status} ${n.statusText}`);return n},Yt=async(e,t,n=W)=>{let r=JSON.stringify({url:e,headers:t}),i=await Et(r,`range-metadata`,n);if(i)return i;let a=!/^https?:/i.test(e),{metadata:o}=await S(e,{fetch,additionalFetchHeaders:t,allowLocalFile:a});return await Dt(r,`range-metadata`,o,n),o},Xt=(e,t)=>{if(e.model.local_path)return l.resolve(e.model.local_path);let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},K=async(e,t)=>{try{let n=await v(e);return t?n.size===t:!0}catch{return!1}},Zt=async(e,t,n,r,i)=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);await G(l.dirname(n));let a=await fetch(e,{headers:t});if(!a.ok||!a.body)throw Error(`Failed to download ${e}: ${a.status} ${a.statusText}`);let o=await m(n,`w`),s=Number(a.headers.get(`content-length`))||r||0,c=0,u=.05;try{await a.body.pipeTo(new ot({async write(e){if(await o.write(e),c+=e.byteLength,typeof i==`function`&&s>0){let e=Math.min(1,c/s);for(;e>=u;)i(u),u+=.05}},async close(){await o.close(),typeof i==`function`&&i(1)},async abort(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}}))}catch(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}if(r){let e=await v(n);if(e.size!==r)throw await y(n).catch(()=>{}),Error(`Downloaded file size mismatch, expected ${r} got ${e.size}`)}},Qt=async e=>{let t=e.model.repo_id||e.model.repository||e.model.model;if(!t)throw Error("`model.repo_id` is required in Buttress backend config");let n=e.model.revision||`main`,r=e.runtime.cache_dir,i=JSON.stringify({repoId:t,revision:n,filename:e.model.filename,url:e.model.url,quantization:e.model.quantization,preferred_quantizations:e.model.preferred_quantizations}),a=await Et(i,`artifact-info`,r);if(a)return a;let o={...e.runtime.http_headers||{}};if(e.runtime.huggingface_token&&(o.Authorization=`Bearer ${e.runtime.huggingface_token}`),e.model.url){let a=await Jt(e.model.url,{headers:o}),s=Number(a.headers.get(`content-length`))||null,c={repoId:t,revision:n,filename:e.model.filename||e.model.url.split(`/`).pop(),url:e.model.url,size:s,headers:o};return await Dt(i,`artifact-info`,c,r),c}let{filename:s}=e.model,c=e.model.quantization&&String(e.model.quantization).toLowerCase(),l=await qt(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),u=l?.siblings||l?.files||[],d=[];for(let e of u){let t=e.rfilename||e.path||e.filename;typeof t==`string`&&t.endsWith(`.gguf`)&&d.push(t)}if(d.length===0)throw Error(`No GGUF artifacts found in repo ${t}`);let f=e.model.preferred_quantizations.length>0?e.model.preferred_quantizations:dt,p=d.map(e=>e.toLowerCase()),m=()=>{for(let e of f){let t=p.findIndex(t=>t.includes(e));if(t!==-1)return{filename:d[t],quantization:e}}return null};if(s)c||=St(s);else{let{filename:e,quantization:t}=m()||{filename:d[0],quantization:null};s=e,c=t||St(s)}let h=`${e.model.base_url.replace(/\/+$/,``)}/${t}/resolve/${n}/${s}`,g=/-(\d{5})-of-(\d{5})\.gguf$/,_=s.match(g),v=null;if(_){let[,,r]=_,i=await qt(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),a=i?.siblings||i?.files||[],c=Number(r);v=0;for(let e=1;e<=c;e+=1){let t=String(e).padStart(5,`0`),n=s.replace(g,`-${t}-of-${r}.gguf`),i=a.find(e=>(e.rfilename||e.path||e.filename)===n),o=Number(i?.size);Number.isFinite(o)&&o>0&&(v+=o)}}else{let e=await Jt(h,{headers:o});v=Number(e.headers.get(`content-length`))||null}let y={repoId:t,revision:n,filename:s,url:h,size:v,quantization:c,headers:o,isSplit:!!_,splitCount:_?Number(_[2]):0};return await Dt(i,`artifact-info`,y,r),y},$t=/^mmproj-.*\.gguf$/i,en=async(e,t)=>{if(!e.model.enable_mtmd)return null;let n=e.runtime.cache_dir,r={...e.runtime.http_headers||{}};e.runtime.huggingface_token&&(r.Authorization=`Bearer ${e.runtime.huggingface_token}`);let i=t?.repoId||e.model.repo_id,a=t?.revision||e.model.revision||`main`,o=JSON.stringify({kind:`mmproj`,repoId:i,revision:a,mmproj_filename:e.model.mmproj_filename,mmproj_url:e.model.mmproj_url,mmproj_local_path:e.model.mmproj_local_path}),s=await Et(o,`artifact-info`,n);if(s)return s;if(e.model.mmproj_url){let t=await Jt(e.model.mmproj_url,{headers:r}),s=Number(t.headers.get(`content-length`))||null,c={repoId:i,revision:a,filename:e.model.mmproj_filename||e.model.mmproj_url.split(`/`).pop(),url:e.model.mmproj_url,size:s,headers:r};return await Dt(o,`artifact-info`,c,n),c}if(e.model.mmproj_local_path){if(!e.model.allow_local_file)throw Error("`model.mmproj_local_path` requires `model.allow_local_file = true`");let t={repoId:i,revision:a,filename:l.basename(e.model.mmproj_local_path),url:null,size:null,headers:r,localPath:l.resolve(e.model.mmproj_local_path)};return await Dt(o,`artifact-info`,t,n),t}if(!i)throw Error("Cannot derive mmproj artifact without `model.repo_id`");let c=await qt(`${e.model.api_base}/models/${i}?revision=${a}&blobs=true`,{headers:r}),u=c?.siblings||c?.files||[],d=u.map(e=>e.rfilename||e.path||e.filename).filter(e=>typeof e==`string`),f=e.model.mmproj_filename;if(f){if(!d.includes(f))throw Error(`mmproj file "${f}" not found in repo ${i}`)}else{let e=d.filter(e=>$t.test(e));if(e.length===0)return console.warn(`[buttress] enable_mtmd set but no mmproj file found in ${i}; skipping multimodal load`),null;let n=t?.quantization&&String(t.quantization).toLowerCase();f=n&&e.find(e=>e.toLowerCase().includes(n))||e[0]}let p=`${e.model.base_url.replace(/\/+$/,``)}/${i}/resolve/${a}/${f}`,m=u.find(e=>(e.rfilename||e.path||e.filename)===f),h=Number(m?.size);if(!Number.isFinite(h)||h<=0){let e=await Jt(p,{headers:r});h=Number(e.headers.get(`content-length`))||null}let g={repoId:i,revision:a,filename:f,url:p,size:h,headers:r};return await Dt(o,`artifact-info`,g,n),g},tn=(e,t)=>{if(t?.localPath)return t.localPath;if(!t)return null;let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},nn=async(e,{modelBytes:t=null,kvCacheBytes:n=null}={})=>{let r=Ct(e),[i,...a]=r,o=e.backend?.gpu_memory_fraction==null?vt.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(e.backend.gpu_memory_fraction))),s=e.backend?.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),c=await ke({platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-llm`,variant:i||null,preferVariants:a,gpuMemoryFraction:o,cpuMemoryFraction:s,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:t,kvCacheBytes:n}),l=e=>({...e,devices:Array.isArray(e.devices)?e.devices:[],ok:e.ok,hasGpu:!!e.hasGpu,totalMemory:e.gpuTotalBytes||e.totalMemory||0,error:e.ok?null:Error(e.error||`Variant ${e.variant} not available on this platform`)});if(!c.ok||!c.selected){let e=(c.attempts||[]).map(e=>`${e.variant}: ${e.error||`unknown error`}`).join(`; `);throw Error(`Unable to initialize any backend variant (${r.join(`, `)}). Errors: ${e}`)}let u=(c.attempts||[]).map(l);return{selected:l(c.selected),attempts:u}},rn=async e=>{let t=await Qt(e),n=await en(e,t),r=await Yt(t.url,t.headers,e.runtime.cache_dir),{arch:i,nCtxTrain:a,nLayer:o,nEmbd:s,nHead:c,nHeadKv:l,nEmbdHeadK:u,nEmbdHeadV:d,quantVersion:f,fileType:p,attentionLayerCount:m,recurrentLayerCount:h,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C}=Ke(r),w=Number.isFinite(Number(o))?Number(o):0,T=Number.isFinite(Number(s))?Number(s):0,E=Number.isFinite(Number(c))?Number(c):0,D=Number.isFinite(Number(l))?Number(l):E,ee=E>0&&T>0?T/E:128,te=u!=null&&Number.isFinite(Number(u))?Number(u):ee,ne=d!=null&&Number.isFinite(Number(d))?Number(d):ee,O=ze({arch:i,metadata:r,nLayer:w}),re=O&&Number.isFinite(Number(O.kvLayers))?Number(O.kvLayers):w,k=Math.max(0,Math.floor(Number(re)||0)),A={use_mmap:e.model.use_mmap??e.runtime.use_mmap,use_mlock:e.model.use_mlock??e.runtime.use_mlock,no_extra_bufts:e.model.no_extra_bufts??e.runtime.no_extra_bufts,n_threads:e.model.n_threads??e.runtime.n_threads,n_ctx:e.model.n_ctx??e.runtime.n_ctx,n_batch:e.model.n_batch??e.runtime.n_batch,n_ubatch:e.model.n_ubatch??e.runtime.n_ubatch,n_cpu_moe:e.model.n_cpu_moe??e.runtime.n_cpu_moe,n_parallel:(e.model.n_parallel??e.runtime.n_parallel)||4,cpu_mask:e.model.cpu_mask??e.runtime.cpu_mask,cpu_strict:e.model.cpu_strict??e.runtime.cpu_strict,devices:e.model.devices??e.runtime.devices,n_gpu_layers:e.model.n_gpu_layers??e.runtime.n_gpu_layers,flash_attn_type:e.model.flash_attn_type??e.runtime.flash_attn_type,cache_type_k:e.model.cache_type_k??e.runtime.cache_type_k,cache_type_v:e.model.cache_type_v??e.runtime.cache_type_v,kv_unified:e.model.kv_unified??e.runtime.kv_unified,swa_full:e.model.swa_full??e.runtime.swa_full,ctx_shift:e.model.ctx_shift??e.runtime.ctx_shift,...ht(e)},j=A.n_ctx?Number(A.n_ctx):null,M=j||a||4096,N=[],P=[],ie=!0;if(j&&a&&j>a){ie=!1;let e=`Requested context length (${j}) exceeds model training context (${a})`;N.push(e),P.push(e),M=a}j&&!a&&N.push(`Model metadata missing training context length, using requested value`);let F={k:A.cache_type_k,v:A.cache_type_v},I=t.size>0?t.size:0,L=qe({layerCount:k,headKvCount:D,embdHeadKCount:te,embdHeadVCount:ne,cacheTypes:F,swaConfig:O,kvUnified:A.kv_unified,nParallel:A.n_parallel,swaFull:A.swa_full,arch:i,attentionLayerCount:m}),R=Je({nLayer:w,nEmbd:T,recurrentLayerCount:h,nSeqMax:A.n_parallel||4,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C,arch:i}),z=await nn(e,{modelBytes:I,kvCacheBytes:L(M)+R}),ae=z.selected.totalMemory||0,oe=ae*(e.backend.gpu_memory_fraction||1),se=e.backend.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),ce=Math.max(0,x.totalmem()*se),le=z.selected.hasGpu?oe:ce,B=Ye({maxCtx:M,availableMemory:le,modelBytes:I,kvBytesForCtx:L});if(!j&&B){let e=a?Math.min(B,a):B,t=Math.max(32,e);t<M&&N.push(`Context length capped to ${t} by memory limits`),M=t}M>B&&(M=B);let ue=Math.floor(B);console.log(`[buttress] Memory-limited context length: ${ue}`);let de=L(M),fe=I+de+R,pe=w?I/(w+1):I,me=0;z.selected.hasGpu&&pe>0&&(me=Math.min(w+1,Math.max(0,Math.floor(oe/pe)))),console.log(`[buttress] Auto GPU layer capacity (${z.selected.variant}): ${me}/${w+1}`);let he;he=A.n_gpu_layers===`auto`||A.n_gpu_layers==null?me:Math.max(0,Math.min(Number(A.n_gpu_layers)||0,w+1));let ge=(()=>{let e=A.flash_attn_type&&String(A.flash_attn_type).toLowerCase();return e===`on`||e===`off`?e:z.selected.hasGpu?`auto`:`off`})(),_e=e.runtime.cache_dir,ve=Xt(e,t),ye=await K(ve,t.size),be=tn(e,n),xe=be?await K(be,n?.size):!1,Se=n?{enabled:!0,initialized:!1,filename:n.filename,url:n.url,sizeBytes:n.size,localPath:be,exists:xe,useGpu:e.model.mmproj_use_gpu,imageMinTokens:e.model.mmproj_image_min_tokens,imageMaxTokens:e.model.mmproj_image_max_tokens}:{enabled:!1,requested:!!e.model.enable_mtmd};return{config:e,info:{ok:ie,backend:`ggml-llm`,warnings:N,errors:P,model:{repoId:t.repoId,revision:t.revision,filename:t.filename,quantization:t.quantization,url:t.url,sizeBytes:t.size,metadata:{architecture:i,n_ctx_train:a,n_layer:w,n_embd:T,quantization_version:f,file_type:p,kv_layer_count:k,swa:O?.enabled?{window:O.window,pattern:O.pattern,dense_first:O.denseFirst,type:O.type,layers:O.swaLayers}:null}},runtime:{...A,variant:z.selected.variant,n_ctx:M,requested_ctx:j,n_gpu_layers:he,auto_gpu_layers:me,flash_attn_type:ge,cache_type_k:F.k,cache_type_v:F.v,estimated_max_n_ctx:ue},resources:{modelBytes:I,kvCacheBytes:de,recurrentMemoryBytes:R,totalEstimatedBytes:fe,gpuCapacityBytes:ae,gpuUsableBytes:oe,cpuUsableBytes:ce,fit:z.selected.fit},devices:{selected:z.selected,attempts:z.attempts},download:{cacheDir:_e,localPath:ve,exists:ye},multimodal:Se,timestamp:new Date().toISOString()},artifact:t,mmprojArtifact:n,mmprojLocalPath:be,mmprojLocalExists:xe,metadata:{arch:i,nCtxTrain:a,nLayer:w,nEmbd:T},devices:z,cacheTypes:F,localPath:ve,localExists:ye}},an=(e,t,n=null,r=null)=>{let i,a=Date.now(),o=0;return new at({async start(s){try{let c=await e.parallel.completion(t,(e,t)=>{t&&(t.token&&(o+=1),s.enqueue({event:`token`,data:{requestId:e,...t}}))}),{requestId:l}=c;i=c.stop;let u=await c.promise;console.log(`[Completion] Result:`,u),s.enqueue({event:`result`,data:{requestId:l,...u}}),s.close();let d=Date.now()-a,f=u.timings||{};H.addCompletion({id:`completion-${l}`,generatorId:n,requestId:l,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:r?.variant||null,cacheTokens:f.cache_n??0,promptTokens:f.prompt_n??0,tokensGenerated:f.predicted_n??o,tokensPerSecond:f.predicted_per_second??0,promptPerSecond:f.prompt_per_second??0,durationMs:d,success:!0,interrupted:u.interrupted||!1,contextFull:u.context_full||u.contextFull||!1})}catch(e){s.enqueue({event:`error`,data:{message:e?.message||String(e)}}),s.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:n,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:r?.variant||null,durationMs:Date.now()-a,tokensGenerated:o,success:!1,error:e?.message||String(e)})}},cancel(){i&&i()}})},on=(e,t,n,r,i,a,o=null,s=null,c=null)=>{let l,u=``,d=!1,f=Date.now(),p=0,m=()=>{i&&y(i).catch(()=>{}),c&&y(c).catch(()=>{})};return new at({async start(h){try{let g=await e.parallel.completion(t,(e,t)=>{t&&(t.token&&(u+=t.token,p+=1),h.enqueue({event:`token`,data:{requestId:e,...t}}))}),{requestId:_}=g;l=g.stop;let v=await g.promise;v.text?u=v.text:v.content&&(u=v.content),d=!v.interrupted&&!v.context_full,console.log(`[Completion] Result:`,v),h.enqueue({event:`result`,data:{requestId:_,...v}}),h.close();let y=Date.now()-f,b=v.timings||{};H.addCompletion({id:`completion-${_}`,generatorId:o,requestId:_,repoId:s?.repoId||null,quantization:s?.quantization||null,variant:s?.variant||null,cacheTokens:b.cache_n??0,promptTokens:b.prompt_n??a??0,tokensGenerated:b.predicted_n??p,tokensPerSecond:b.predicted_per_second??0,promptPerSecond:b.prompt_per_second??0,durationMs:y,success:!0,interrupted:v.interrupted||!1,contextFull:v.context_full||v.contextFull||!1,usedCache:!!t.load_state_path}),d&&n.enabled&&u?n.saveCompletionState(r,u,i,a,c).catch(e=>{console.warn(`[SessionCache] Save failed:`,e.message)}):m()}catch(e){h.enqueue({event:`error`,data:{message:e?.message||String(e)}}),h.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:o,repoId:s?.repoId||null,quantization:s?.quantization||null,variant:s?.variant||null,durationMs:Date.now()-f,tokensGenerated:p,success:!1,error:e?.message||String(e)}),m()}},cancel(){l&&l(),m()}})},sn=e=>{let t={model:e.plan.localPath,runtime:e.plan.info.runtime};return s(`sha256`).update(JSON.stringify(t)).digest(`hex`).slice(0,24)},cn=async(e,t,n,r=null)=>{let{config:i,localPath:a,artifact:o}=e;if(e.localExists&&!t.has(a))return e.info.download.exists=!0,typeof n==`function`&&n(.5),a;if(i.model.local_path&&!i.model.allow_local_file)throw Error("Local model path provided but `model.allow_local_file` is not enabled");let s=a;if(r){let t=r.getDownload(s);if(t){console.log(`[ensureModelFile] Waiting for global download: ${o.repoId}`);try{if(await t,await K(a,o.size))return e.localExists=!0,e.info.download.exists=!0,typeof n==`function`&&n(.5),a}catch(e){console.warn(`[ensureModelFile] Global download failed, will retry: ${e.message}`)}}}t.has(s)||t.set(s,(async()=>{if(o.isSplit&&o.splitCount>0){let e=/-(\d{5})-of-(\d{5})\.gguf$/,t=l.dirname(a),r=o.splitCount,s=0;for(let a=1;a<=r;a+=1){let c=String(a).padStart(5,`0`),u=o.filename.replace(e,`-${c}-of-${String(r).padStart(5,`0`)}.gguf`),d=`${i.model.base_url.replace(/\/+$/,``)}/${o.repoId}/resolve/${o.revision}/${u}`,f=l.join(t,u);await K(f)||await Zt(d,o.headers,f,null,e=>{if(e>=0&&Number.isFinite(e)){let t=(s+e)/r,i=Math.round(t*100);console.log(`Downloading model splits: ${Math.min(100,i)}%`),typeof n==`function`&&n(t*.5)}}),s+=1}}else console.log(`Downloading model: 0%`),await Zt(o.url,o.headers,a,o.size,e=>{if(e>=0&&Number.isFinite(e)){let t=Math.round(e*100);console.log(`Downloading model: ${Math.min(100,t)}%`),typeof n==`function`&&n(e*.5)}});e.localExists=!0,e.info.download.exists=!0})());try{await t.get(s)}finally{t.delete(s)}return a},ln=async(e,t,n,r=null)=>{let{mmprojArtifact:i,mmprojLocalPath:a}=e;if(!i||!a)return null;if(i.localPath){if(!await K(a))throw Error(`mmproj local file not found: ${a}`);return e.mmprojLocalExists=!0,e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a}if(e.mmprojLocalExists&&!t.has(a))return e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a;let o=a;if(r){let t=r.getDownload(o);if(t)try{if(await t,await K(a,i.size))return e.mmprojLocalExists=!0,e.info.multimodal.exists=!0,typeof n==`function`&&n(1),a}catch(e){console.warn(`[ensureMmprojFile] Global download failed, will retry: ${e.message}`)}}t.has(o)||t.set(o,(async()=>{console.log(`Downloading mmproj: 0%`),await Zt(i.url,i.headers,a,i.size,e=>{if(e>=0&&Number.isFinite(e)){let t=Math.round(e*100);console.log(`Downloading mmproj: ${Math.min(100,t)}%`),typeof n==`function`&&n(e)}}),e.mmprojLocalExists=!0,e.info.multimodal.exists=!0})());try{await t.get(o)}finally{t.delete(o)}return a},un=async(e,t)=>{let n=sn(e),r=e.contexts.get(n);if(r&&!r.released)return r.releaseTimer&&(clearTimeout(r.releaseTimer),r.releaseTimer=null,console.log(`[Context] Cancelled pending release for context "${n}"`)),r.releaseRequested=!1,r.refCount+=1,console.log(`[Context] Reusing existing context "${n}", refCount=${r.refCount}`),typeof t==`function`&&t(0),r.context||await r.ready,typeof t==`function`&&t(1),r;r?console.log(`[Context] Record exists but released=${r.released}, creating new context`):console.log(`[Context] No existing record for "${n}", creating new context`),r={key:n,refCount:1,ready:null,released:!1},e.contexts.set(n,r),r.ready=(async()=>{let i=Date.now(),a=await cn(e.plan,e.downloads,t,e.globalDownloadManager);typeof t==`function`&&t(.5);let o={model:a,n_threads:e.plan.info.runtime.n_threads,use_mmap:e.plan.info.runtime.use_mmap,use_mlock:e.plan.info.runtime.use_mlock,no_extra_bufts:e.plan.info.runtime.no_extra_bufts,cpu_mask:e.plan.info.runtime.cpu_mask,cpu_strict:e.plan.info.runtime.cpu_strict,devices:e.plan.info.runtime.devices,n_ctx:e.plan.info.runtime.n_ctx,n_gpu_layers:e.plan.info.runtime.n_gpu_layers,n_parallel:e.plan.info.runtime.n_parallel,n_batch:e.plan.info.runtime.n_batch,n_ubatch:e.plan.info.runtime.n_ubatch,n_cpu_moe:e.plan.info.runtime.n_cpu_moe,flash_attn_type:e.plan.info.runtime.flash_attn_type,ctx_shift:e.plan.info.runtime.ctx_shift,kv_unified:e.plan.info.runtime.kv_unified,swa_full:e.plan.info.runtime.swa_full,lib_variant:e.plan.info.runtime.variant};for(let t of pt){let n=e.plan.info.runtime[t];n!=null&&(o[t]=n)}e.plan.info.runtime.flash_attn_type!==`off`&&(o.cache_type_k=e.plan.info.runtime.cache_type_k,o.cache_type_v=e.plan.info.runtime.cache_type_v),console.log(`[Context] Load Options:`,o);let s;try{if(s=await T(o,e=>{typeof t==`function`&&(t(.5+e*.25),e%5==0&&console.log(`[Context] Load Model Progress:`,e))}),e.plan.info.runtime.n_parallel&&!await s.parallel.enable({n_parallel:e.plan.info.runtime.n_parallel,n_batch:e.plan.info.runtime.n_batch}))throw Error(`Failed to enable parallel decoding mode for context`);if(e.plan.mmprojArtifact){let t=await ln(e.plan,e.downloads,null,e.globalDownloadManager);if(t){let n=e.config.model.mmproj_use_gpu,r={path:t,use_gpu:n==null?(e.plan.info.runtime.n_gpu_layers||0)>0:!!n,image_min_tokens:e.config.model.mmproj_image_min_tokens,image_max_tokens:e.config.model.mmproj_image_max_tokens};console.log(`[Context] initMultimodal:`,r),await s.initMultimodal(r)?e.plan.info.multimodal.initialized=!0:console.warn(`[Context] initMultimodal returned false; multimodal disabled`)}}return typeof t==`function`&&t(1),r.context=s,r.modelInfo=s.getModelInfo(),H.addModelLoad({id:`${e.id}-${n}`,generatorId:e.id,contextKey:n,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,variant:e.plan.info.runtime?.variant||null,nCtx:e.plan.info.runtime?.n_ctx||null,nGpuLayers:e.plan.info.runtime?.n_gpu_layers||null,durationMs:Date.now()-i,success:!0}),r}catch(t){if(H.addModelLoad({id:`${e.id}-${n}`,generatorId:e.id,contextKey:n,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,variant:e.plan.info.runtime?.variant||null,durationMs:Date.now()-i,success:!1,error:t?.message||String(t)}),s)try{s.release()}catch{}throw t}})();try{return await r.ready,r}catch(t){throw e.contexts.delete(n),t}},dn=async(e,t,n=!1)=>{if(t.released||!n&&t.refCount>0)return!1;t.released=!0,e.contexts.delete(t.key);try{t.context?.parallel?.disable?.()}catch{}return await t.context?.release?.(),!0},fn=async(e,t,n=!1)=>{if(t.releaseRequested=!0,t.releaseTimer&&=(clearTimeout(t.releaseTimer),null),n)t.refCount=0;else if(t.refCount=Math.max(0,t.refCount-1),t.refCount>0)return t.releaseRequested=!1,!1;let r=e.config.runtime.context_release_delay_ms;if(typeof r!=`number`||!Number.isFinite(r))return dn(e,t);let i=Math.max(0,Math.floor(r));return n||i<=0?dn(e,t):(console.log(`[Context] Scheduling release in ${i}ms for context "${t.key}"`),t.releaseTimer=setTimeout(async()=>{if(t.releaseTimer=null,t.refCount>0){console.log(`[Context] Release cancelled, refCount=${t.refCount} for context "${t.key}"`),t.releaseRequested=!1;return}console.log(`[Context] Releasing context "${t.key}" after ${i}ms delay`),await dn(e,t)},i),!0)};async function pn(e,t,n={}){let{globalDownloadManager:r=null}=n,i=xt(t),a=await rn(i),o=new Kt(i,a);await o.initialize();let s={id:e,type:`ggml-llm`,config:i,plan:a,info:a.info,contexts:new Map,downloads:new Map,globalDownloadManager:r,sessionCache:o,finalized:!1};return{id:e,type:`ggml-llm`,info:a.info,contexts:s.contexts,initContext:async(e={})=>{let{onProgress:t}=e,n=await un(s,t);return s.sessionCache.updateModelInfo(n.modelInfo),{modelInfo:n.modelInfo?{...n.modelInfo}:null,runtime:{...s.plan.info.runtime},download:{...s.plan.info.download},multimodal:s.plan.info.multimodal?{...s.plan.info.multimodal}:null}},completion:async(e={})=>{let{options:t={},useCache:n=!0}=e,r=_t(t,s.plan.info.runtime),i=sn(s),a=s.contexts.get(i);if(!a)throw Error(`Context "${i}" not initialized`);await a.ready;let o=r.prompt||``,c=null,l=null;if(!o&&r.messages){({messages:c}=r),l={chatTemplate:r.chat_template||r.chatTemplate,jinja:r.jinja??!0,tools:r.tools,parallel_tool_calls:r.parallel_tool_calls,tool_choice:r.tool_choice,reasoning_format:r.reasoning_format,enable_thinking:r.enable_thinking,add_generation_prompt:r.add_generation_prompt,now:r.now,chat_template_kwargs:r.chat_template_kwargs,force_pure_content:r.force_pure_content};let e=await a.context.getFormattedChat(c,l.chatTemplate,l);o=e?.prompt||e||``}if(n&&s.sessionCache.enabled&&o){let{options:e}=await s.sessionCache.prepareCompletionOptions(r,o,a.context),t=await s.sessionCache.generateTempStatePath(),n=(await a.context.tokenize(o))?.tokens?.length||0,i={...e,save_state_path:t},c=s.sessionCache.requiresExactMatch(),l=!!i.load_state_path,u=null;c&&!l&&(u=await s.sessionCache.generateTempStatePath(),i.save_prompt_state_path=u);let d={repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null};return on(a.context,i,s.sessionCache,o,t,n,s.id,d,u)}let u={repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null};return an(a.context,r,s.id,u)},tokenize:async(e={})=>{let{text:t=``,params:n={}}=e,r=sn(s),i=s.contexts.get(r);if(!i)throw Error(`Context "${r}" not initialized`);await i.ready;let a=await i.context.tokenize(t,n);if(!a)return{tokens:[]};let o=Array.from(a.tokens??[],Number);return{...a,tokens:o}},detokenize:async(e={})=>{let{tokens:t=[]}=e,n=sn(s),r=s.contexts.get(n);if(!r)throw Error(`Context "${n}" not initialized`);await r.ready;let i=t.map(e=>Number(e));return r.context.detokenize(i)},applyChatTemplate:async(e={})=>{let{messages:t=[],template:n,params:r}=e,i=sn(s),a=s.contexts.get(i);if(!a)throw Error(`Context "${i}" not initialized`);return await a.ready,await a.context.getFormattedChat(t,n,r)},releaseContext:async()=>{if(s.finalized)return!1;let e=sn(s),t=s.contexts.get(e);return t?fn(s,t,!1):!1},finalize:async()=>{if(s.finalized)return;s.finalized=!0;let e=Array.from(s.contexts.values()),t=e.map(e=>e.released||e.releaseRequested||e.releaseTimer||(e.refCount=Math.max(0,e.refCount-1),e.refCount>0)?Promise.resolve(!1):dn(s,e));await Promise.allSettled(t),(e.length===0||e.every(e=>e.released))&&await s.sessionCache.cleanup()},getStatus:()=>{let e=[],t=Array.from(s.contexts.entries()).map(([t,n])=>{let r={key:t,refCount:n.refCount,hasModel:!!n.context},i=n.context.parallel.getStatus();return r.parallelStatus=i,e.push({contextKey:t,...i}),r});return{id:s.id,type:s.type,repoId:s.plan.info.model?.repoId||null,quantization:s.plan.info.model?.quantization||null,variant:s.plan.info.runtime?.variant||null,nCtx:s.plan.info.runtime?.n_ctx||null,nParallel:s.plan.info.runtime?.n_parallel||null,contexts:t,parallelStatuses:e}},subscribeParallelStatus:e=>{let t=Array.from(s.contexts.entries()).map(([t,n])=>n.context.parallel.subscribeToStatus(n=>{e({contextKey:t,...n})}));return{remove:()=>{t.forEach(e=>{e?.remove&&e.remove()})}}},hasPendingReleases:()=>Array.from(s.contexts.values()).some(e=>!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0)),resetFinalized:()=>{s.finalized=!1}}}const mn=e=>{let t=xt(e);return t.model.repo_id||t.model.repository||t.model.model||null};async function hn(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n;try{let n=xt(e),o=await Qt(n),s=Xt(n,o),{repoId:c}=o,u=await en(n,o).catch(e=>(console.warn(`[Download] Failed to derive mmproj artifact: ${e.message}`),null)),d=tn(n,u),f=async()=>{if(!u||!d||u.localPath)return;if(await K(d,u.size)){console.log(`[Download] mmproj already exists: ${d}`);return}let e=t.getDownload(d);if(e){await e;return}let n=(async()=>{try{await Zt(u.url,u.headers,d,u.size,e=>{e>=0&&Number.isFinite(e)&&console.log(`[Download] mmproj ${c}: ${Math.round(e*100)}%`)})}finally{t.deleteDownload(d)}})();t.setDownload(d,n),await n};if(await K(s,o.size))return console.log(`[Download] Model already exists: ${c} at ${s}`),await f().catch(e=>{console.error(`[Download] mmproj download failed: ${e.message}`),typeof a==`function`&&a(e)}),typeof i==`function`&&i({localPath:s,repoId:c,alreadyExists:!0}),{started:!1,localPath:s,repoId:c,alreadyExists:!0};let p=t.getDownload(s);if(p)return console.log(`[Download] Already downloading: ${c}`),p.then(()=>{typeof i==`function`&&i({localPath:s,repoId:c,joinedExisting:!0})}).catch(e=>{typeof a==`function`&&a(e)}),{started:!1,localPath:s,repoId:c,alreadyDownloading:!0};console.log(`[Download] Starting download: ${c}`);let m=(async()=>{try{if(o.isSplit&&o.splitCount>0){let e=/-(\d{5})-of-(\d{5})\.gguf$/,t=l.dirname(s),i=o.splitCount,a=0;for(let s=1;s<=i;s+=1){let u=String(s).padStart(5,`0`),d=o.filename.replace(e,`-${u}-of-${String(i).padStart(5,`0`)}.gguf`),f=`${n.model.base_url.replace(/\/+$/,``)}/${o.repoId}/resolve/${o.revision}/${d}`,p=l.join(t,d);await K(p)||await Zt(f,o.headers,p,null,e=>{if(e>=0&&Number.isFinite(e)){let t=(a+e)/i;console.log(`[Download] ${c}: ${Math.round(t*100)}%`),typeof r==`function`&&r(t)}}),a+=1}}else await Zt(o.url,o.headers,s,o.size,e=>{e>=0&&Number.isFinite(e)&&(console.log(`[Download] ${c}: ${Math.round(e*100)}%`),typeof r==`function`&&r(e))});await f(),console.log(`[Download] Completed: ${c}`),typeof i==`function`&&i({localPath:s,repoId:c})}catch(e){throw console.error(`[Download] Failed: ${c}`,e.message),typeof a==`function`&&a(e),e}finally{t.deleteDownload(s)}})();return t.setDownload(s,m),{started:!0,localPath:s,repoId:c}}catch(e){return console.error(`[Download] Failed to start download:`,e.message),typeof a==`function`&&a(e),{started:!1,localPath:null,repoId:null,error:e.message}}}async function gn(e){let t=xt(e),n=await Qt(t),r=await Yt(n.url,n.headers,t.runtime.cache_dir),{arch:i,nCtxTrain:a,nLayer:o,nEmbd:s,nHead:c,nHeadKv:l,nEmbdHeadK:u,nEmbdHeadV:d,quantVersion:f,fileType:p,attentionLayerCount:m,recurrentLayerCount:h,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C}=Ke(r),w=Number.isFinite(Number(o))?Number(o):0,T=Number.isFinite(Number(s))?Number(s):0,E=Number.isFinite(Number(c))?Number(c):0,D=Number.isFinite(Number(l))?Number(l):E,ee=E>0&&T>0?T/E:128,te=u!=null&&Number.isFinite(Number(u))?Number(u):ee,ne=d!=null&&Number.isFinite(Number(d))?Number(d):ee,O=ze({arch:i,metadata:r,nLayer:w}),re=O&&Number.isFinite(Number(O.kvLayers))?Number(O.kvLayers):w,k=Math.max(0,Math.floor(Number(re)||0)),A=(t.model.n_ctx?Number(t.model.n_ctx):null)||a||4096,j={k:t.model.cache_type_k,v:t.model.cache_type_v},M=n.size>0?n.size:0,N=t.model.n_parallel||4,P=qe({layerCount:k,headKvCount:D,embdHeadKCount:te,embdHeadVCount:ne,cacheTypes:j,swaConfig:O,kvUnified:t.model.kv_unified,nParallel:N,swaFull:t.model.swa_full,arch:i,attentionLayerCount:m}),ie=Je({nLayer:w,nEmbd:T,recurrentLayerCount:h,nSeqMax:N,ssmDConv:g,ssmDState:_,ssmDInner:v,ssmNGroup:y,ssmDtRank:b,rwkvHeadSize:S,rwkvTokenShiftCount:C,arch:i}),F=t.backend?.gpu_memory_fraction==null?vt.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(t.backend.gpu_memory_fraction))),I=t.backend?.cpu_memory_fraction==null?ft:Math.min(1,Math.max(0,Number(t.backend.cpu_memory_fraction))),L=await nn(t,{modelBytes:M,kvCacheBytes:P(A)}),R=(L.selected.totalMemory||0)*F,z=Math.max(0,x.totalmem()*I),ae=Ye({maxCtx:A,availableMemory:L.selected.hasGpu?R:z,modelBytes:M,kvBytesForCtx:P}),oe=P(A),se=P(ae);return{kvInfo:{nCtxTrain:a,nLayer:w,nEmbd:T,nHeadKv:D,nEmbdHeadK:te,nEmbdHeadV:ne,nHeadCount:E,nHeadKvCount:D,kvLayerCount:k,swa:O?.enabled?{window:O.window,pattern:O.pattern,denseFirst:O.denseFirst,type:O.type,layers:O.swaLayers}:null},modelBytes:M,kvCacheBytes:oe,limitedKvCacheBytes:se,memoryLimitedCtx:ae,recurrentMemoryBytes:ie,quantization:{name:n.quantization||null,fileType:p,version:f}}}const _n=e=>e?typeof e.score==`number`&&Number.isFinite(e.score)?Number(e.score):ue(e):0;async function vn(e=null,t={}){let{threshold:n=1.1,includeBreakdown:r=!1,config:i,...a}=t,o=null,s=null,c=null,l=null,u=null,d=null,f=null;if(i)try{let{modelBytes:e,kvCacheBytes:t,limitedKvCacheBytes:n,memoryLimitedCtx:r,recurrentMemoryBytes:a,kvInfo:p,quantization:m}=await gn(i);o=e,s=t,c=n,l=r,u=a,d=p,f=m}catch{}let p=i?.backend?.gpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.gpu_memory_fraction))),m=i?.backend?.cpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.cpu_memory_fraction))),h=await ke({...a,platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-llm`,includeBreakdown:r,gpuMemoryFraction:p,cpuMemoryFraction:m,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:o,kvCacheBytes:s,limitedKvCacheBytes:c}),g=h.selected,_=_n(g);g.modelBytes=o||null,g.kvCacheBytes=s||null,g.memoryLimitedCtx=l||null,g.limitedKvCacheBytes=c||null,g.recurrentMemoryBytes=u||null,g.kvInfo=d||null,g.quantization=f||null;let v=null,y=null;if(e){let t=_n(e);y={...e,score:t};let r=`buttress`,i=`buttress-higher-score`;if(!h.ok)r=`local`,i=`buttress-unavailable`;else if(!t&&t!==0)r=`buttress`,i=`missing-client-score`;else{let e=y.fit,a=y.limitedFit,o=g?.fit,s=g?.limitedFit,c=e?.fitsInGpu||e?.fitsInCpu||a?.fitsInGpu||a?.fitsInCpu,l=o?.fitsInGpu||o?.fitsInCpu||s?.fitsInGpu||s?.fitsInCpu;c&&!l?(r=`local`,i=`client-fits-in-memory`):l&&!c?(r=`buttress`,i=`buttress-fits-in-memory`):t>_*n?(r=`local`,i=`client-better`):_>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`)}v={buttressScore:_,clientScore:t,threshold:n,recommendation:r,reason:i}}!h.ok&&!v&&(v={buttressScore:_,clientScore:e?.score??null,threshold:n,recommendation:`local`,reason:`buttress-unavailable`});let b=null;return i&&(b={repoId:i.model?.repo_id||null,quantization:i.model?.quantization||null,nCtx:i.model?.n_ctx||null,cacheKType:i.model?.cache_type_k||`f16`,cacheVType:i.model?.cache_type_v||`f16`}),{type:`ggml-llm`,timestamp:new Date().toISOString(),buttress:h,client:y,comparison:v,modelConfig:b}}const{WritableStream:yn}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,bn=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),bn(e[t],n)):e[t]=n}),e),xn=`https://huggingface.co`,Sn=`https://huggingface.co/api`,Cn=l.join(x.homedir(),`.buttress`,`models`),wn=[`cuda`,`vulkan`,`default`],Tn=[`q8_0`,`q5_1`,`q5_0`,`q4_1`,`q4_0`],En=`fp16`,Dn=.5,On=[`large-v3-turbo`,`distil-large-v3`,`large-v3`,`large-v2`,`large-v1`,`large`,`distil-medium`,`medium.en`,`medium`,`small.en-tdrz`,`distil-small.en`,`small.en`,`small`,`base.en`,`base`,`tiny.en`,`tiny`],kn=e=>{if(!e)return null;let t=e.toLowerCase();return On.find(e=>t.includes(e))||null},An={backend:{type:`ggml-stt`,variant:null,variant_preference:wn,gpu_memory_fraction:.85,cpu_memory_fraction:Dn},model:{repo_id:`BricksDisplay/whisper-ggml`,revision:`main`,filename:null,url:null,quantization:null,preferred_quantizations:[`q8_0`,En,`q5_1`],allow_local_file:!1,local_path:null,api_base:Sn,base_url:xn,use_gpu:!0,use_flash_attn:`auto`},runtime:{cache_dir:Cn,prefer_variants:[],huggingface_token:process.env.HUGGINGFACE_TOKEN||null,http_headers:{},max_threads:null,context_release_delay_ms:1e4}},jn=(e,t=[])=>!e&&e!==0?[...t]:Array.isArray(e)?e.filter(e=>e!=null):[e],Mn=e=>{if(!e)return null;let t=String(e).toLowerCase();return[`cuda`,`vulkan`,`default`].includes(t)?t:null},Nn=(e={})=>{let t=structuredClone(An);if(bn(t,e),t.backend.variant=Mn(t.backend.variant),t.backend.variant_preference=Array.from(new Set(jn(t.backend.variant_preference||wn).flatMap(e=>{let t=Mn(e);return t?[t]:[]}))),t.backend.variant_preference.length===0&&(t.backend.variant_preference=[...wn]),t.runtime.prefer_variants=Array.from(new Set(jn(t.runtime.prefer_variants).flatMap(e=>{let t=Mn(e);return t?[t]:[]}))),t.model.preferred_quantizations=Array.from(new Set(jn(t.model.preferred_quantizations||t.model.quantizations).flatMap(e=>{let t=e?String(e).toLowerCase():null;return t?[t]:[]}))),t.model.quantization){let e=String(t.model.quantization).toLowerCase();t.model.preferred_quantizations.includes(e)||t.model.preferred_quantizations.unshift(e)}return t.model.base_url=t.model.base_url||xn,t.model.api_base=t.model.api_base||Sn,t.runtime.cache_dir=t.runtime.cache_dir?l.resolve(t.runtime.cache_dir):Cn,t.runtime.context_release_delay_ms=Math.max(0,Number(t.runtime.context_release_delay_ms)||An.runtime.context_release_delay_ms),t},Pn=e=>{let t=e.toLowerCase();return Tn.find(e=>t.includes(e))||null},Fn=e=>{let t=[];e.backend.variant&&t.push(e.backend.variant),e.runtime.prefer_variants.length>0&&t.push(...e.runtime.prefer_variants),t.push(...e.backend.variant_preference),t.push(`default`);let n=new Set;for(let e of t){let t=Mn(e);t&&n.add(t)}return Array.from(n)},In=async e=>{await p(e,{recursive:!0})},Ln=(e=Cn)=>l.join(e,`.metadata-cache`),Rn=(e,t,n=Cn)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(Ln(n),t,`${r}.json`)},zn=async(e,t,n=Cn)=>{try{let r=await h(Rn(e,t,n),`utf-8`);return JSON.parse(r)}catch{return null}},Bn=async(e,t,n,r=Cn)=>{try{let i=Rn(e,t,r);await In(l.dirname(i)),await b(i,JSON.stringify(n),`utf-8`)}catch{}},Vn=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,t);if(!n.ok){let t=await n.text().catch(()=>``);throw Error(`Failed to fetch ${e}: ${n.status} ${n.statusText} ${t}`.trim())}return n.json()},Hn=async(e,t={})=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);let n=await fetch(e,{...t,method:`HEAD`});if(!n.ok)throw Error(`Failed to fetch headers for ${e}: ${n.status} ${n.statusText}`);return n},Un=(e,t)=>{if(e.model.local_path)return l.resolve(e.model.local_path);let n=t.repoId.split(`/`),r=l.join(e.runtime.cache_dir,...n,t.revision);return l.join(r,t.filename)},Wn=async(e,t)=>{try{let n=await v(e);return t?n.size===t:!0}catch{return!1}},Gn=async(e,t,n,r,i)=>{if(typeof fetch!=`function`)throw Error(`Global fetch is not available in this runtime`);await In(l.dirname(n));let a=await fetch(e,{headers:t});if(!a.ok||!a.body)throw Error(`Failed to download ${e}: ${a.status} ${a.statusText}`);let o=await m(n,`w`),s=Number(a.headers.get(`content-length`))||r||0,c=0,u=.05;try{await a.body.pipeTo(new yn({async write(e){if(await o.write(e),c+=e.byteLength,typeof i==`function`&&s>0){let e=Math.min(1,c/s);for(;e>=u;)i(u),u+=.05}},async close(){await o.close(),typeof i==`function`&&i(1)},async abort(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}}))}catch(e){throw await o.close().catch(()=>{}),await y(n).catch(()=>{}),e}if(r){let e=await v(n);if(e.size!==r)throw await y(n).catch(()=>{}),Error(`Downloaded file size mismatch, expected ${r} got ${e.size}`)}},Kn=async e=>{let t=e.model.repo_id||e.model.repository||e.model.model;if(!t)throw Error("`model.repo_id` is required in Buttress backend config");let n=e.model.revision||`main`,r=e.runtime.cache_dir,i=JSON.stringify({repoId:t,revision:n,filename:e.model.filename,url:e.model.url,quantization:e.model.quantization,preferred_quantizations:e.model.preferred_quantizations}),a=await zn(i,`artifact-info`,r);if(a)return a;let o={...e.runtime.http_headers||{}};if(e.runtime.huggingface_token&&(o.Authorization=`Bearer ${e.runtime.huggingface_token}`),e.model.url){let a=await Hn(e.model.url,{headers:o}),s=Number(a.headers.get(`content-length`))||null,c=e.model.filename||e.model.url.split(`/`).pop(),l={repoId:t,revision:n,filename:c,url:e.model.url,size:s,quantization:Pn(c||``),headers:o};return await Bn(i,`artifact-info`,l,r),l}let{filename:s}=e.model,c=e.model.quantization&&String(e.model.quantization).toLowerCase(),l=await Vn(`${e.model.api_base}/models/${t}?revision=${n}&blobs=true`,{headers:o}),u=(l?.siblings||l?.files||[]).map(e=>e.rfilename||e.path||e.filename).filter(e=>typeof e==`string`&&e.endsWith(`.bin`));if(u.length===0)throw Error(`No model artifacts found in repo ${t}`);let d=e.model.preferred_quantizations.length>0?e.model.preferred_quantizations:Tn,f=()=>{for(let e of d)if(e===En){let e=u.find(e=>{let t=e.toLowerCase();return!Tn.some(e=>t.includes(e))});if(e)return{filename:e,quantization:null}}else{let t=u.find(t=>t.toLowerCase().includes(e));if(t)return{filename:t,quantization:e}}return null};if(s)c||=Pn(s);else{let{filename:e,quantization:t}=f()||{filename:u[0],quantization:null};s=e,c=t||Pn(s)}let p=`${e.model.base_url.replace(/\/+$/,``)}/${t}/resolve/${n}/${s}`,m=await Hn(p,{headers:o}),h=Number(m.headers.get(`content-length`))||null,g={repoId:t,revision:n,filename:s,url:p,size:h,quantization:c,headers:o,isSplit:!1,splitCount:0};return await Bn(i,`artifact-info`,g,r),g},qn=async(e,{modelBytes:t=null,processingBytes:n=null}={})=>{let r=Fn(e),[i,...a]=r,o=e.backend?.gpu_memory_fraction==null?An.backend.gpu_memory_fraction||1:Math.min(1,Math.max(0,Number(e.backend.gpu_memory_fraction))),s=e.backend?.cpu_memory_fraction==null?Dn:Math.min(1,Math.max(0,Number(e.backend.cpu_memory_fraction))),c=await ke({platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-stt`,variant:i||null,preferVariants:a,variantPreference:e.backend.variant_preference,gpuMemoryFraction:o,cpuMemoryFraction:s,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:t,kvCacheBytes:n}),l=e=>({...e,devices:Array.isArray(e.devices)?e.devices:[],ok:e.ok,hasGpu:!!e.hasGpu,totalMemory:e.gpuTotalBytes||e.totalMemory||0,error:e.ok?null:Error(e.error||`Variant ${e.variant} not available on this platform`)});if(!c.ok||!c.selected){let e=(c.attempts||[]).map(e=>`${e.variant}: ${e.error||`unknown error`}`).join(`; `);throw Error(`Unable to initialize any backend variant (${r.join(`, `)}). Errors: ${e}`)}let u=(c.attempts||[]).map(l);return{selected:l(c.selected),attempts:u}},Jn=async e=>{let t=await Kn(e),n=Ne({modelBytes:t.size>0?t.size:0}),r=await qn(e,{modelBytes:n.modelBytes,processingBytes:n.processingBufferBytes}),i=r.selected.hasGpu&&(r.selected.fit?.fitsInGpu===void 0?!0:r.selected.fit.fitsInGpu);e.model.use_gpu===!1&&(i=!1);let a=e.model.use_flash_attn&&String(e.model.use_flash_attn).toLowerCase(),o;o=a===`on`||a===`true`?!0:a===`off`||a===`false`?!1:i;let s=e.runtime.cache_dir,c=Un(e,t),l=await Wn(c,t.size);return{config:e,info:{ok:!0,backend:`ggml-stt`,model:{repoId:t.repoId,revision:t.revision,filename:t.filename,quantization:t.quantization,modelType:kn(t.filename),url:t.url,sizeBytes:t.size},runtime:{variant:r.selected.variant,use_gpu:i,use_flash_attn:o,max_threads:e.runtime.max_threads?Number(e.runtime.max_threads):null},resources:{...n,gpuCapacityBytes:r.selected.gpuTotalBytes,gpuUsableBytes:r.selected.gpuUsableBytes,cpuUsableBytes:r.selected.cpuUsableBytes,fit:r.selected.fit},devices:{selected:r.selected,attempts:r.attempts},download:{cacheDir:s,localPath:c,exists:l},timestamp:new Date().toISOString()},artifact:t,memory:n,devices:r,localPath:c,localExists:l}},Yn=async(e,t,n,r=null)=>{let{localPath:i,artifact:a,config:o}=e;if(e.localExists)return typeof n==`function`&&n(1),i;if(r){let t=r.getDownload(i);if(t){console.log(`[ensureModelFile] Waiting for global STT download: ${a.repoId}`);try{if(await t,await Wn(i,a.size))return e.localExists=!0,e.info.download.exists=!0,typeof n==`function`&&n(1),i}catch(e){console.warn(`[ensureModelFile] Global STT download failed, will retry: ${e.message}`)}}}let s=t.get(i);if(s)return await s,typeof n==`function`&&n(1),i;let c=(async()=>{if(o.model.allow_local_file){if(!await Wn(i,a.size))throw Error(`Local model file not found: ${i}`);return i}return await Gn(a.url,a.headers,i,a.size,n),i})();t.set(i,c);try{return await c,i}finally{t.delete(i)}};var Xn=class{constructor(){this.queue=[],this.processing=!1,this.currentTaskId=null}async enqueue(e,t=null){return new Promise((n,r)=>{this.queue.push({task:e,resolve:n,reject:r,taskId:t}),this.processNext()})}async processNext(){if(this.processing||this.queue.length===0)return;this.processing=!0;let{task:e,resolve:t,reject:n,taskId:r}=this.queue.shift();this.currentTaskId=r;try{t(await e())}catch(e){n(e)}finally{this.processing=!1,this.currentTaskId=null,this.processNext()}}getStatus(){return{processing:this.processing,queuedCount:this.queue.length,currentTaskId:this.currentTaskId}}};const Zn=e=>{if(!e)return null;if(e instanceof ArrayBuffer)return e;if(ArrayBuffer.isView(e))return e.buffer;if(typeof e==`string`){let t=e.startsWith(`data:`)?e.split(`,`)[1]||``:e,n=Buffer.from(t,`base64`);return n.buffer.slice(n.byteOffset,n.byteOffset+n.byteLength)}throw Error(`Unsupported audioData format, expected base64 string or ArrayBuffer`)},Qn=async(e,t)=>{if(e.contextRecord&&!e.contextRecord.released)return e.contextRecord.releaseTimer&&(clearTimeout(e.contextRecord.releaseTimer),e.contextRecord.releaseTimer=null,console.log(`[Context] Cancelled pending STT release`)),e.contextRecord.releaseRequested=!1,e.contextRecord.refCount+=1,console.log(`[Context] Reusing existing STT context, refCount=${e.contextRecord.refCount}`),typeof t==`function`&&t(0),e.contextRecord.context||await e.contextRecord.ready,typeof t==`function`&&t(1),e.contextRecord;e.contextRecord?console.log(`[Context] STT record exists but released=${e.contextRecord.released}, creating new context`):console.log(`[Context] No existing STT record, creating new context`);let n={refCount:1,ready:null,released:!1};e.contextRecord=n,n.ready=(async()=>{let r=Date.now();try{typeof t==`function`&&t(0);let i=await Yn(e.plan,e.downloads,t,e.globalDownloadManager);typeof t==`function`&&t(.5);let a=await ee({filePath:i,useFlashAttn:!!e.plan.info.runtime.use_flash_attn,useGpu:!!e.plan.info.runtime.use_gpu,nThreads:e.plan.info.runtime.max_threads},e.plan.info.runtime.variant);typeof t==`function`&&t(1),n.context=a;try{n.modelInfo=a.getModelInfo()}catch{n.modelInfo=null}return U.addModelLoad({id:e.id,generatorId:e.id,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,modelType:e.plan.info.model?.modelType||null,variant:e.plan.info.runtime?.variant||null,useGpu:e.plan.info.runtime?.use_gpu||!1,durationMs:Date.now()-r,success:!0}),n}catch(t){throw U.addModelLoad({id:e.id,generatorId:e.id,repoId:e.plan.info.model?.repoId||null,quantization:e.plan.info.model?.quantization||null,modelType:e.plan.info.model?.modelType||null,variant:e.plan.info.runtime?.variant||null,durationMs:Date.now()-r,success:!1,error:t?.message||String(t)}),t}})();try{return await n.ready,typeof t==`function`&&t(1),n}catch(t){throw e.contextRecord=null,t}},$n=async(e,t,n=!1)=>t.released||!n&&t.refCount>0?!1:(t.released=!0,e.contextRecord=null,await t.context?.release?.(),!0),er=async(e,t,n=!1)=>{if(t.releaseRequested=!0,t.releaseTimer&&=(clearTimeout(t.releaseTimer),null),n)t.refCount=0;else if(t.refCount=Math.max(0,t.refCount-1),t.refCount>0)return t.releaseRequested=!1,!1;let r=e.config.runtime.context_release_delay_ms;if(typeof r!=`number`||!Number.isFinite(r))return $n(e,t);let i=Math.max(0,Math.floor(r));return n||i<=0?$n(e,t):(console.log(`[Context] Scheduling STT release in ${i}ms`),t.releaseTimer=setTimeout(async()=>{if(t.releaseTimer=null,t.refCount>0){console.log(`[Context] STT release cancelled, refCount=${t.refCount}`),t.releaseRequested=!1;return}console.log(`[Context] Releasing STT context after ${i}ms delay`),await $n(e,t)},i),!0)};async function tr(e,t,n={}){let{globalDownloadManager:r=null}=n,i=Nn(t),a=await Jn(i),o={id:e,type:`ggml-stt`,config:i,plan:a,info:a.info,contextRecord:null,downloads:new Map,globalDownloadManager:r,queue:new Xn,finalized:!1},s=async()=>{if(o.finalized)return;o.finalized=!0;let e=o.contextRecord;e&&(e.released||e.releaseRequested||e.releaseTimer||(e.refCount=Math.max(0,e.refCount-1),!(e.refCount>0)&&await $n(o,e)))},c=async(e={})=>{let{onProgress:t}=e;try{let e=await Qn(o,t);return{modelInfo:e.modelInfo&&typeof e.modelInfo==`object`?{...e.modelInfo}:null,runtime:{...o.plan.info.runtime},download:{...o.plan.info.download}}}catch(e){throw console.error(`[Context] Error initializing context:`,e),e}},u=async()=>{if(o.finalized)return!1;let e=o.contextRecord;return e?er(o,e):!1},d=async(e={})=>{let{audioPath:t,audioData:n,options:r={}}=e,i=o.contextRecord;if(!i)throw Error(`Context not initialized`);let a={...r};o.plan.info.runtime.max_threads&&a.maxThreads==null&&(a.maxThreads=o.plan.info.runtime.max_threads);let s=`transcription-${Date.now()}-${Math.random().toString(36).slice(2,8)}`,c=Date.now();return o.queue.enqueue(async()=>{await i.ready;try{let e;if(n){let t=Zn(n),{promise:r}=i.context.transcribeData(t,a);e=await r}else{if(!t)throw Error(`audioPath or audioData is required for transcription`);let n=l.resolve(t),{promise:r}=i.context.transcribe(n,a);e=await r}return U.addTranscription({id:s,generatorId:o.id,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,durationMs:Date.now()-c,segmentCount:e?.segments?.length||0,textLength:e?.text?.length||0,success:!0}),e}catch(e){throw U.addTranscription({id:s,generatorId:o.id,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,durationMs:Date.now()-c,success:!1,error:e?.message||String(e)}),e}},s)};return{id:e,type:`ggml-stt`,info:a.info,queue:o.queue,initContext:c,transcribe:async(e={})=>d(e),transcribeData:async(e={})=>d(e),releaseContext:u,finalize:s,getStatus:()=>({id:o.id,type:o.type,repoId:o.plan.info.model?.repoId||null,quantization:o.plan.info.model?.quantization||null,modelType:o.plan.info.model?.modelType||null,variant:o.plan.info.runtime?.variant||null,hasContext:!!o.contextRecord?.context,contextRefCount:o.contextRecord?.refCount||0,queueStatus:o.queue.getStatus()}),hasPendingReleases:()=>{let e=o.contextRecord;return e?!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0):!1},resetFinalized:()=>{o.finalized=!1}}}const nr=e=>{let t=Nn(e),n=t.model.repo_id||t.model.repository||t.model.model||null;if(!n)return null;let r=kn(t.model.filename);return r?`${n}:${r}`:n};async function rr(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n;try{let n=Nn(e),o=await Kn(n),s=Un(n,o),{repoId:c}=o;if(await Wn(s,o.size))return console.log(`[Download] STT model already exists: ${c} at ${s}`),typeof i==`function`&&i({localPath:s,repoId:c,alreadyExists:!0}),{started:!1,localPath:s,repoId:c,alreadyExists:!0};let l=t.getDownload(s);if(l)return console.log(`[Download] Already downloading STT model: ${c}`),l.then(()=>{typeof i==`function`&&i({localPath:s,repoId:c,joinedExisting:!0})}).catch(e=>{typeof a==`function`&&a(e)}),{started:!1,localPath:s,repoId:c,alreadyDownloading:!0};console.log(`[Download] Starting STT model download: ${c}`);let u=(async()=>{try{await Gn(o.url,o.headers,s,o.size,e=>{e>=0&&Number.isFinite(e)&&(console.log(`[Download] ${c}: ${Math.round(e*100)}%`),typeof r==`function`&&r(e))}),console.log(`[Download] Completed STT model: ${c}`),typeof i==`function`&&i({localPath:s,repoId:c})}catch(e){throw console.error(`[Download] Failed STT model: ${c}`,e.message),typeof a==`function`&&a(e),e}finally{t.deleteDownload(s)}})();return t.setDownload(s,u),{started:!0,localPath:s,repoId:c}}catch(e){return console.error(`[Download] Failed to start STT download:`,e.message),typeof a==`function`&&a(e),{started:!1,localPath:null,repoId:null,error:e.message}}}const ir=e=>e?typeof e.score==`number`&&Number.isFinite(e.score)?Number(e.score):ue(e):0;async function ar(e=null,t={}){let{threshold:n=1.1,includeBreakdown:r=!1,config:i,...a}=t,o=null,s=null,c=null;if(i)try{let e=await Kn(Nn(i));o=e.size??null,{processingBufferBytes:s}=Ne({modelBytes:o}),c=e.quantization||null}catch{}let l=i?.backend?.gpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.gpu_memory_fraction))),u=i?.backend?.cpu_memory_fraction==null?void 0:Math.min(1,Math.max(0,Number(i.backend.cpu_memory_fraction))),d=await ke({...a,platform:process.platform,totalMemoryInBytes:x.totalmem(),backend:`ggml-stt`,includeBreakdown:r,gpuMemoryFraction:l,cpuMemoryFraction:u,dependencies:{getBackendDevicesInfo:C,isLibVariantAvailable:w},modelBytes:o,kvCacheBytes:s}),f=d.selected,p=ir(f);f&&(f.modelBytes=o||null,f.processingBytes=s||null,f.quantization=c||null);let m=null,h=null;if(e){let t=ir(e);h={...e,score:t};let r=`buttress`,i=`buttress-higher-score`;if(!d.ok)r=`local`,i=`buttress-unavailable`;else if(!t&&t!==0)r=`buttress`,i=`missing-client-score`;else if(e.fit&&f?.fit){let a=e.fit.fitsInGpu||e.fit.fitsInCpu,o=f.fit.fitsInGpu||f.fit.fitsInCpu;a&&!o?(r=`local`,i=`client-fits-in-memory`):o&&!a?(r=`buttress`,i=`buttress-fits-in-memory`):t>p*n?(r=`local`,i=`client-better`):p>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`)}else t>p*n?(r=`local`,i=`client-better`):p>t*n?(r=`buttress`,i=`buttress-better`):(r=`either`,i=`comparable-scores`);m={buttressScore:p,clientScore:t,threshold:n,recommendation:r,reason:i}}!d.ok&&!m&&(m={buttressScore:p,clientScore:e?.score??null,threshold:n,recommendation:`local`,reason:`buttress-unavailable`});let g=null;return i&&(g={repoId:i.model?.repo_id||null,quantization:i.model?.quantization||null,filename:i.model?.filename||null}),{type:`ggml-stt`,timestamp:new Date().toISOString(),buttress:d,client:h,comparison:m,modelConfig:g}}const{ReadableStream:or}=typeof globalThis<`u`&&globalThis.ReadableStream&&globalThis.WritableStream?{ReadableStream:globalThis.ReadableStream,WritableStream:globalThis.WritableStream}:u,sr=te(import.meta.url),cr=l.dirname(sr),lr=l.join(cr,`mlx-bridge.py`),ur=`mlx-vlm==0.4.0`,dr=`mlx-lm==0.31.1`,fr=l.join(x.homedir(),`.buttress`,`models`),pr={backend:{type:`mlx-llm`},model:{repo_id:null,revision:`main`,adapter_path:null,tokenizer_config:null,model_config:null,vlm:`auto`},runtime:{cache_dir:fr,huggingface_token:process.env.HUGGINGFACE_TOKEN||null,mlx_env_dir:null,mlx_lm_package:dr,mlx_vlm_package:ur,context_release_delay_ms:1e4,session_cache:{enabled:!0,max_size_bytes:5*1024*1024*1024,max_entries:100}}},mr=(e,t)=>e==null?t:typeof e==`number`?e:typeof e==`string`?E.parse(e)??t:t,hr=(e={},t={})=>(Object.entries(t||{}).forEach(([t,n])=>{n&&typeof n==`object`&&!Array.isArray(n)?((!e[t]||typeof e[t]!=`object`)&&(e[t]={}),hr(e[t],n)):e[t]=n}),e),gr=(e={})=>{let t=structuredClone(pr);return hr(t,e),t},_r=async(e,t={})=>{let n=await fetch(e,t);if(!n.ok)throw Error(`HTTP ${n.status}: ${e}`);return n.json()},vr=async e=>{await p(e,{recursive:!0})},yr=(e,t,n)=>{let r=s(`sha256`).update(e).digest(`hex`);return l.join(n,`.metadata-cache`,t,`${r}.json`)},br=async(e,t,n)=>{try{let r=await h(yr(e,t,n),`utf-8`);return JSON.parse(r)}catch{return null}},xr=async(e,t,n,r)=>{try{let i=yr(e,t,r);await vr(l.dirname(i)),await b(i,JSON.stringify(n),`utf-8`)}catch{}};async function Sr(e,{revision:t=`main`,cacheDir:n,token:r}={}){let i=JSON.stringify({repoId:e,revision:t,type:`mlx-model-metadata`});if(n){let e=await br(i,`mlx-model-metadata`,n);if(e)return e}let a={};r&&(a.Authorization=`Bearer ${r}`);let o=(await _r(`https://huggingface.co/api/models/${e}?revision=${t}&blobs=true`,{headers:a}))?.siblings||[],s=0;for(let e of o){let t=e.rfilename||e.path||e.filename||``;/\.(safetensors|npz)$/.test(t)&&(s+=Number(e.size)||0)}let c=null;try{c=await _r(`https://huggingface.co/${e}/raw/${t}/config.json`,{headers:a})}catch{}let l=c?.text_config||c||{},u=c||{},d=u.model_type||u.architectures?.[0]||null,f=l.hidden_size||l.dim||0,p=l.num_hidden_layers||l.n_layers||0,m=l.num_attention_heads||l.n_heads||0,h=l.num_key_value_heads??m,g=l.vocab_size||0,_=l.max_position_embeddings||0,v=l.intermediate_size||0,y=l.head_dim||l.v_head_dim||(m>0&&f>0&&Number.isInteger(f/m)?f/m:0),b=l.kv_lora_rank||0,x=l.qk_rope_head_dim||0,S=b>0,C=u.quantization||u.quantization_config||null,w=C?.bits||null,T=C?.group_size||null,E=l.dtype||u.torch_dtype||(w?`${w}bit`:null),D={repoId:e,revision:t,modelBytes:s,arch:d,hiddenSize:f,numLayers:p,numHeads:m,numKvHeads:h,headDim:y,vocabSize:g,maxCtx:_,intermediateSize:v,quantBits:w,quantGroupSize:T,dtype:E,isMLA:S,kvLoraRank:b,qkRopeHeadDim:x,fileCount:o.length,config:c};return n&&await xr(i,`mlx-model-metadata`,D,n),D}function Cr({numLayers:e,numKvHeads:t,headDim:n,contextLength:r,isMLA:i,kvLoraRank:a,qkRopeHeadDim:o}){return!e||!r?0:i&&a>0?e*(a+(o||0))*r*2:!t||!n?0:e*t*n*r*2*2}const wr=async e=>{try{return await v(e),!0}catch{return!1}},q=(e,t,n={})=>new Promise((r,i)=>{ne(e,t,{timeout:n.timeout||3e5,...n},(t,n,a)=>{if(t){let n=a?.toString().trim()||t.message;i(Error(`${e} failed: ${n}`))}else r({stdout:n?.toString()||``,stderr:a?.toString()||``})})}),Tr=new Map;async function Er({envDir:e,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r}){let i=l.resolve(e),a=Tr.get(i);if(a){let e=await a;return r?.(1),e}let o=Or({envDir:i,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r});Tr.set(i,o);try{return await o}finally{Tr.delete(i)}}const Dr=[3,10];async function Or({envDir:e,mlxLmPackage:t,mlxVlmPackage:n,onProgress:r}){let i=l.join(e,`bin`,`python3`),a=l.join(e,`bin`,`pip`);if(await wr(i))try{return await q(i,[`-c`,`import mlx_vlm; import torch`],{timeout:1e4}),r?.(1),i}catch{}if(!await wr(i)){r?.(.1);try{let{stdout:e}=await q(`python3`,[`-c`,`import sys; print(f"{sys.version_info.major}.{sys.version_info.minor}")`],{timeout:5e3}),[t,n]=e.trim().split(`.`).map(Number);(t<Dr[0]||t===Dr[0]&&n<Dr[1])&&console.warn(`[mlx-llm] WARNING: System Python is ${t}.${n}, but mlx-vlm requires >= ${Dr.join(`.`)}. You may get an older mlx-vlm version with reduced functionality. Consider installing Python >= 3.10 (e.g. via Homebrew).`)}catch{}console.log(`[mlx-llm] Creating venv at ${e}`),await p(e,{recursive:!0}),await q(`python3`,[`-m`,`venv`,e],{timeout:6e4}),r?.(.3)}return console.log(`[mlx-llm] Installing ${n}`),r?.(.4),await q(a,[`install`,t,n,`torch`,`torchvision`],{timeout:6e5,env:{...process.env}}),r?.(.9),await q(i,[`-c`,`import mlx_vlm; import torch; print(mlx_vlm.__version__)`],{timeout:15e3}),r?.(1),console.log(`[mlx-llm] mlx-vlm installed successfully`),i}var kr=class{constructor(){this.process=null,this.pendingRequests=new Map,this.requestCounter=0,this.readyPromise=null,this.buffer=``}spawn(e){return this.process=re(e,[lr],{stdio:[`pipe`,`pipe`,`pipe`],env:{...process.env,PYTHONUNBUFFERED:`1`}}),this.process.stderr.on(`data`,e=>{let t=e.toString().trim();t&&console.log(t)}),this.process.on(`exit`,e=>{console.log(`[mlx-llm] Bridge process exited with code ${e}`);for(let[t,n]of this.pendingRequests)n.reject(Error(`Bridge process exited (code ${e})`)),this.pendingRequests.delete(t);this.process=null}),this.process.stdout.on(`data`,e=>{this.buffer+=e.toString();let t=this.buffer.split(`
 `);this.buffer=t.pop();for(let e of t)if(e.trim())try{this.handleMessage(JSON.parse(e))}catch(t){console.error(`[mlx-llm] Failed to parse bridge message:`,e,t)}}),this.readyPromise=new Promise((e,t)=>{this.pendingRequests.set(`__init__`,{resolve:()=>e(),reject:t}),setTimeout(()=>t(Error(`Bridge startup timeout`)),3e4)}),this.readyPromise}handleMessage(e){let t=this.pendingRequests.get(e.id);t&&(e.error?(t.reject(Error(e.error.message)),this.pendingRequests.delete(e.id)):e.event?e.event===`result`?(t.resolve(e.data),this.pendingRequests.delete(e.id)):t.onEvent?.(e.event,e.data):e.result!==void 0&&(t.resolve(e.result),this.pendingRequests.delete(e.id)))}async call(e,t={}){if(!this.process)throw Error(`Bridge not running`);let n=String(++this.requestCounter);return new Promise((r,i)=>{this.pendingRequests.set(n,{resolve:r,reject:i}),this.write({id:n,method:e,params:t})})}stream(e,t,n){if(!this.process)throw Error(`Bridge not running`);let r=String(++this.requestCounter);return{id:r,promise:new Promise((i,a)=>{this.pendingRequests.set(r,{resolve:i,reject:a,onEvent:n}),this.write({id:r,method:e,params:t})})}}cancel(e){this.process&&this.write({id:`cancel-${e}`,method:`cancel`,params:{request_id:e}})}write(e){this.process?.stdin?.write(JSON.stringify(e)+`
-`)}kill(){this.process&&=(this.process.kill(),null),this.pendingRequests.clear()}get alive(){return this.process!=null&&!this.process.killed}};function Ar(){let e=[];return process.platform!==`darwin`&&e.push(`MLX requires macOS (Apple Silicon)`),x.arch()!==`arm64`&&e.push(`MLX requires Apple Silicon (arm64)`),e}function jr(e){let t=Ar();return{config:e,info:{ok:t.length===0,backend:`mlx-llm`,warnings:[],errors:[...t],model:{repoId:e.model.repo_id,revision:e.model.revision},runtime:{variant:`mlx`},resources:{},devices:{selected:{variant:`mlx`,hasGpu:!0}},download:{cacheDir:e.runtime.cache_dir,localPath:null,exists:!1},timestamp:new Date().toISOString()}}}const Mr=e=>{if(!e)return[];let t=[];for(let n of e)if(Array.isArray(n.content))for(let e of n.content)e.type===`image_url`&&e.image_url?.url&&t.push(e.image_url.url);return t};var Nr=class{constructor(){this.queue=[],this.processing=!1,this.currentTaskId=null}async enqueue(e,t=null){return new Promise((n,r)=>{this.queue.push({task:e,resolve:n,reject:r,taskId:t}),this.processNext()})}async processNext(){if(this.processing||this.queue.length===0)return;this.processing=!0;let{task:e,resolve:t,reject:n,taskId:r}=this.queue.shift();this.currentTaskId=r;try{t(await e())}catch(e){n(e)}finally{this.processing=!1,this.currentTaskId=null,this.processNext()}}getStatus(){return{processing:this.processing,queuedCount:this.queue.length,currentTaskId:this.currentTaskId}}};const Pr=`</think>`;function Fr(e,t){if(!t)return{reasoningContent:``,content:e};let n=e.indexOf(Pr);if(n!==-1)return{reasoningContent:e.slice(0,n).replace(/^\n+/,``),content:e.slice(n+8).replace(/^\n+/,``)};let r=e.length;for(let t=1;t<=8&&t<=e.length;t++)if(Pr.startsWith(e.slice(-t))){r=e.length-t;break}return{reasoningContent:e.slice(0,r).replace(/^\n+/,``),content:``}}function Ir(e,t,n,r,{enableThinking:i=!1}={}){let a=null,o=Date.now(),s=0,c=``;return new or({start(l){let{id:u,promise:d}=e.stream(`generate`,t,(e,t)=>{if(e===`token`){s+=1,c+=t.token||``;let e=Fr(c,i);l.enqueue({event:`token`,data:{requestId:u,token:t.token,token_id:t.token_id,text:c,content:e.content,reasoning_content:e.reasoningContent}})}});a=u,d.then(e=>{let t={prompt_n:e.prompt_tokens??0,prompt_per_second:e.prompt_tps??0,predicted_n:e.generation_tokens??s,predicted_per_second:e.generation_tps??0},a=Fr(c,i);l.enqueue({event:`result`,data:{requestId:u,text:c,content:a.content,reasoning_content:a.reasoningContent,timings:t,prompt_tokens:t.prompt_n,tokens_predicted:t.predicted_n,interrupted:e.interrupted||!1,peak_memory:e.peak_memory}}),l.close(),H.addCompletion({id:`completion-${u}`,generatorId:n,requestId:u,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:`mlx`,promptTokens:t.prompt_n,tokensGenerated:t.predicted_n,tokensPerSecond:t.predicted_per_second,promptPerSecond:t.prompt_per_second,durationMs:Date.now()-o,success:!0,interrupted:e.interrupted||!1})}).catch(e=>{l.enqueue({event:`error`,data:{message:e?.message||String(e)}}),l.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:n,repoId:r?.repoId||null,variant:`mlx`,durationMs:Date.now()-o,tokensGenerated:s,success:!1,error:e?.message||String(e)})})},cancel(){a&&e.cancel(a)}})}async function Lr(e,t,n={}){let r=gr(t),i=jr(r);i.info.ok||console.error(`[mlx-llm] Platform check failed:`,i.info.errors);let a={id:e,type:`mlx-llm`,config:r,plan:i,info:i.info,contexts:new Map,bridge:null,queue:new Nr,finalized:!1},o=`mlx:${r.model.repo_id}`,s=async(e={})=>{let{onProgress:t}=e,n=a.contexts.get(o);if(n&&!n.released)return n.refCount+=1,n.releaseTimer&&=(clearTimeout(n.releaseTimer),null),await n.ready,{modelInfo:n.modelInfo,runtime:{...a.info.runtime},download:{...a.info.download}};let i={key:o,refCount:1,ready:null,released:!1,releaseRequested:!1,releaseTimer:null,modelInfo:null};a.contexts.set(o,i);let s=Date.now();i.ready=(async()=>{let e=r.runtime.cache_dir||fr,n=await Er({envDir:r.runtime.mlx_env_dir||l.join(e,`mlx-env`),mlxLmPackage:r.runtime.mlx_lm_package||dr,mlxVlmPackage:r.runtime.mlx_vlm_package||ur,onProgress:t?e=>t(e*.3):void 0});(!a.bridge||!a.bridge.alive)&&(a.bridge=new kr,await a.bridge.spawn(n)),t?.(.4);let o={model:r.model.repo_id};r.model.revision&&(o.revision=r.model.revision),r.model.adapter_path&&(o.adapter_path=r.model.adapter_path),r.model.vlm!=null&&(o.vlm=r.model.vlm),r.runtime.huggingface_token&&(process.env.HF_TOKEN=r.runtime.huggingface_token),await a.bridge.call(`load`,o),t?.(.9);let c=await a.bridge.call(`get_info`);i.modelInfo={model:c.model,peak_memory:c.peak_memory,active_memory:c.active_memory};let u=r.runtime.session_cache;u?.enabled!==!1&&await a.bridge.call(`configure_cache`,{enabled:!0,cache_dir:l.join(e,`mlx-session-cache`),max_entries:u?.max_entries||100,max_size_bytes:mr(u?.max_size_bytes,5*1024*1024*1024)}),a.info.download.exists=!0,t?.(1),H.addModelLoad({id:`load-${Date.now()}`,generatorId:a.id,repoId:r.model.repo_id,variant:`mlx`,durationMs:Date.now()-s,success:!0})})();try{await i.ready}catch(e){throw i.released=!0,a.contexts.delete(o),H.addModelLoad({id:`load-${Date.now()}`,generatorId:a.id,repoId:r.model.repo_id,variant:`mlx`,durationMs:Date.now()-s,success:!1,error:e?.message||String(e)}),e}return{modelInfo:i.modelInfo,runtime:{...a.info.runtime},download:{...a.info.download}}},c=async e=>{if(e.released)return!1;e.released=!0;try{a.bridge?.alive&&await a.bridge.call(`release`)}catch(e){console.error(`[mlx-llm] Error releasing context:`,e.message)}return a.contexts.delete(e.key),!0};return{id:e,type:`mlx-llm`,info:i.info,contexts:a.contexts,queue:a.queue,initContext:s,completion:async(e={})=>{let{options:t={}}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);await n.ready;let r=Mr(t.messages),i=t.prompt||``;if(!i&&t.messages){let e={messages:t.messages,add_generation_prompt:t.add_generation_prompt??!0,tools:t.tools,...t.chat_template_kwargs};t.enable_thinking!=null&&(e.enable_thinking=t.enable_thinking),i=(await a.bridge.call(`apply_chat_template`,e)).text}let s={prompt:i,max_tokens:t.n_predict??t.max_tokens??256};r.length>0&&(s.image=r),t.temperature!=null&&(s.temperature=t.temperature),t.top_p!=null&&(s.top_p=t.top_p),t.top_k!=null&&(s.top_k=t.top_k),t.min_p!=null&&(s.min_p=t.min_p),t.seed!=null&&(s.seed=t.seed),t.repetition_penalty!=null&&(s.repetition_penalty=t.repetition_penalty),t.stop&&(s.stop=t.stop);let c={repoId:a.info.model?.repoId||null},l=`completion-${Date.now()}-${Math.random().toString(36).slice(2,8)}`;return new or({start(e){a.queue.enqueue(async()=>{let n=Ir(a.bridge,s,a.id,c,{enableThinking:!!t.enable_thinking}).getReader();try{for(;;){let{value:t,done:r}=await n.read();if(r)break;e.enqueue(t)}e.close()}catch(t){throw e.error(t),t}},l).catch(t=>{try{e.error(t)}catch{}})},cancel(){a.bridge?.alive}})},tokenize:async(e={})=>{let{text:t=``}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);return await n.ready,a.bridge.call(`tokenize`,{text:t})},detokenize:async(e={})=>{let{tokens:t=[]}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);return await n.ready,(await a.bridge.call(`detokenize`,{tokens:t})).text},applyChatTemplate:async(e={})=>{let{messages:t=[],params:n={}}=e,r=a.contexts.get(o);if(!r)throw Error(`Context "${o}" not initialized`);await r.ready;let i={messages:t,add_generation_prompt:n.add_generation_prompt??!0,tools:n.tools,...n.chat_template_kwargs};return(await a.bridge.call(`apply_chat_template`,i)).text},releaseContext:async()=>{if(a.finalized)return!1;let e=a.contexts.get(o);if(!e||(e.releaseRequested=!0,e.refCount=Math.max(0,e.refCount-1),e.refCount>0))return!1;let t=r.runtime.context_release_delay_ms??1e4;return t>0?new Promise(n=>{e.releaseTimer=setTimeout(async()=>{e.releaseTimer=null,e.refCount<=0&&!e.released?n(await c(e)):n(!1)},t)}):c(e)},finalize:async()=>{if(a.finalized)return;a.finalized=!0;let e=Array.from(a.contexts.values());for(let t of e)t.released||(t.refCount=0,await c(t));a.bridge?.kill(),a.bridge=null},getStatus:()=>({id:a.id,type:a.type,repoId:a.info.model?.repoId||null,variant:`mlx`,contexts:Array.from(a.contexts.entries()).map(([e,t])=>({key:e,refCount:t.refCount,hasModel:!t.released})),queueStatus:a.queue.getStatus()}),hasPendingReleases:()=>Array.from(a.contexts.values()).some(e=>!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0)),resetFinalized:()=>{a.finalized=!1}}}const Rr=e=>gr(e).model.repo_id||null;async function zr(e=null,t={}){let{includeBreakdown:n=!1,config:r}=t,i=Ar(),a=i.length===0,o=!1,s=!1;if(a){try{await q(`python3`,[`--version`],{timeout:5e3}),o=!0}catch{}if(o)try{await q(`python3`,[`-c`,`import mlx`],{timeout:1e4}),s=!0}catch{}}let c=await De({platform:process.platform,arch:x.arch(),totalMemoryInBytes:x.totalmem(),includeBreakdown:n}),l=null,u=null,d=null,f=null,p=null,m=null,h=null;if(r){let e=gr(r),t=e.model.repo_id;if(t)try{l=await Sr(t,{revision:e.model.revision,cacheDir:e.runtime.cache_dir||fr,token:e.runtime.huggingface_token}),u=l.modelBytes||0,f=l.maxCtx||4096;let n={numLayers:l.numLayers,numKvHeads:l.numKvHeads,headDim:l.headDim,isMLA:l.isMLA,kvLoraRank:l.kvLoraRank,qkRopeHeadDim:l.qkRopeHeadDim};d=Cr({...n,contextLength:f});let r=c.ok?c.selected.gpuUsableBytes:0;if(r>0&&u>0&&l.numLayers){let e=r-u;if(e>0){let t;t=l.isMLA&&l.kvLoraRank>0?l.numLayers*(l.kvLoraRank+(l.qkRopeHeadDim||0))*2:l.numKvHeads&&l.headDim?l.numLayers*l.numKvHeads*l.headDim*2*2:0,t>0&&(m=Math.floor(e/t),m=Math.min(m,f))}else m=0;m!=null&&m<f&&(p=Cr({...n,contextLength:m}))}h={repoId:t,revision:e.model.revision,nCtx:f,architecture:l.arch,quantBits:l.quantBits,quantGroupSize:l.quantGroupSize}}catch{}}let g=c.ok?{...c.selected,modelBytes:u,kvCacheBytes:d,memoryLimitedCtx:m,limitedKvCacheBytes:p,kvInfo:l?{nCtxTrain:l.maxCtx||null,nLayer:l.numLayers,nEmbd:l.hiddenSize,nHeadKv:l.numKvHeads,headDim:l.headDim}:null,quantization:l?{bits:l.quantBits,groupSize:l.quantGroupSize,dtype:l.dtype}:null}:null;if(c.ok&&u!=null&&u>0){let e=u+(d||0),t=c.selected.gpuUsableBytes,n=e<=t;if(g.fit={totalRequiredBytes:e,fitsInGpu:n,fitsInCpu:e<=t,limiting:n?`none`:`insufficient-memory`},p!=null&&p!==d){let e=u+p;g.limitedFit={totalRequiredBytes:e,fitsInGpu:e<=t,fitsInCpu:e<=t,limiting:e<=t?`none`:`insufficient-memory`}}}return{type:`mlx-llm`,available:a,platform:{ok:a,os:process.platform,arch:x.arch(),errors:i},python:{available:o},mlx:{systemAvailable:s,venvSupported:o},buttress:c.ok?{ok:c.ok,selected:g,attempts:c.attempts}:{ok:!1,selected:null,attempts:c.attempts||[],errors:c.errors},modelConfig:h,timestamp:new Date().toISOString()}}async function Br(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n,o=gr(e),s=o.model.repo_id;if(!s)return{started:!1,localPath:null,repoId:null,error:`Missing repo_id`};let c=Ar();if(c.length>0)return{started:!1,localPath:null,repoId:s,error:c.join(`; `)};let u=`mlx:${s}`;if(t?.isDownloading(u))return{started:!1,localPath:null,repoId:s,alreadyDownloading:!0};let d=(async()=>{try{let e=o.runtime.cache_dir||fr,t=await Er({envDir:o.runtime.mlx_env_dir||l.join(e,`mlx-env`),mlxLmPackage:o.runtime.mlx_lm_package||dr,mlxVlmPackage:o.runtime.mlx_vlm_package||ur,onProgress:r?e=>r(e*.3):void 0});r?.(.3);let n=`
+`)}kill(){this.process&&=(this.process.kill(),null),this.pendingRequests.clear()}get alive(){return this.process!=null&&!this.process.killed}};function Ar(){let e=[];return process.platform!==`darwin`&&e.push(`MLX requires macOS (Apple Silicon)`),x.arch()!==`arm64`&&e.push(`MLX requires Apple Silicon (arm64)`),e}function jr(e){let t=Ar();return{config:e,info:{ok:t.length===0,backend:`mlx-llm`,warnings:[],errors:[...t],model:{repoId:e.model.repo_id,revision:e.model.revision},runtime:{variant:`mlx`},resources:{},devices:{selected:{variant:`mlx`,hasGpu:!0}},download:{cacheDir:e.runtime.cache_dir,localPath:null,exists:!1},timestamp:new Date().toISOString()}}}const Mr=e=>{if(!e)return[];let t=[];for(let n of e)if(Array.isArray(n.content))for(let e of n.content)e.type===`image_url`&&e.image_url?.url&&t.push(e.image_url.url);return t};var Nr=class{constructor(){this.queue=[],this.processing=!1,this.currentTaskId=null}async enqueue(e,t=null){return new Promise((n,r)=>{this.queue.push({task:e,resolve:n,reject:r,taskId:t}),this.processNext()})}async processNext(){if(this.processing||this.queue.length===0)return;this.processing=!0;let{task:e,resolve:t,reject:n,taskId:r}=this.queue.shift();this.currentTaskId=r;try{t(await e())}catch(e){n(e)}finally{this.processing=!1,this.currentTaskId=null,this.processNext()}}getStatus(){return{processing:this.processing,queuedCount:this.queue.length,currentTaskId:this.currentTaskId}}};const Pr=`</think>`;function Fr(e,t){if(!t)return{reasoningContent:``,content:e};let n=e.indexOf(Pr);if(n!==-1)return{reasoningContent:e.slice(0,n).replace(/^\n+/,``),content:e.slice(n+8).replace(/^\n+/,``)};let r=e.length;for(let t=1;t<=8&&t<=e.length;t++)if(Pr.startsWith(e.slice(-t))){r=e.length-t;break}return{reasoningContent:e.slice(0,r).replace(/^\n+/,``),content:``}}function Ir(e,t,n,r,{enableThinking:i=!1}={}){let a=null,o=Date.now(),s=0,c=``;return new or({start(l){let{id:u,promise:d}=e.stream(`generate`,t,(e,t)=>{if(e===`token`){s+=1,c+=t.token||``;let e=Fr(c,i);l.enqueue({event:`token`,data:{requestId:u,token:t.token,token_id:t.token_id,text:c,content:e.content,reasoning_content:e.reasoningContent}})}});a=u,d.then(e=>{let t={prompt_n:e.prompt_tokens??0,prompt_per_second:e.prompt_tps??0,predicted_n:e.generation_tokens??s,predicted_per_second:e.generation_tps??0},a=Fr(c,i);l.enqueue({event:`result`,data:{requestId:u,text:c,content:a.content,reasoning_content:a.reasoningContent,timings:t,prompt_tokens:t.prompt_n,tokens_predicted:t.predicted_n,interrupted:e.interrupted||!1,peak_memory:e.peak_memory}}),l.close(),H.addCompletion({id:`completion-${u}`,generatorId:n,requestId:u,repoId:r?.repoId||null,quantization:r?.quantization||null,variant:`mlx`,promptTokens:t.prompt_n,tokensGenerated:t.predicted_n,tokensPerSecond:t.predicted_per_second,promptPerSecond:t.prompt_per_second,durationMs:Date.now()-o,success:!0,interrupted:e.interrupted||!1})}).catch(e=>{l.enqueue({event:`error`,data:{message:e?.message||String(e)}}),l.error(e),H.addCompletion({id:`completion-${Date.now()}`,generatorId:n,repoId:r?.repoId||null,variant:`mlx`,durationMs:Date.now()-o,tokensGenerated:s,success:!1,error:e?.message||String(e)})})},cancel(){a&&e.cancel(a)}})}async function Lr(e,t,n={}){let r=gr(t),i=jr(r);i.info.ok||console.error(`[mlx-llm] Platform check failed:`,i.info.errors);let a={id:e,type:`mlx-llm`,config:r,plan:i,info:i.info,contexts:new Map,bridge:null,queue:new Nr,finalized:!1},o=`mlx:${r.model.repo_id}`,s=async(e={})=>{let{onProgress:t}=e,n=a.contexts.get(o);if(n&&!n.released)return n.refCount+=1,n.releaseTimer&&=(clearTimeout(n.releaseTimer),null),await n.ready,{modelInfo:n.modelInfo,runtime:{...a.info.runtime},download:{...a.info.download}};let i={key:o,refCount:1,ready:null,released:!1,releaseRequested:!1,releaseTimer:null,modelInfo:null};a.contexts.set(o,i);let s=Date.now();i.ready=(async()=>{let e=r.runtime.cache_dir||fr,n=await Er({envDir:r.runtime.mlx_env_dir||l.join(e,`mlx-env`),mlxLmPackage:r.runtime.mlx_lm_package||dr,mlxVlmPackage:r.runtime.mlx_vlm_package||ur,onProgress:t?e=>t(e*.3):void 0});(!a.bridge||!a.bridge.alive)&&(a.bridge=new kr,await a.bridge.spawn(n)),t?.(.4);let o={model:r.model.repo_id};r.model.revision&&(o.revision=r.model.revision),r.model.adapter_path&&(o.adapter_path=r.model.adapter_path),r.model.vlm!=null&&(o.vlm=r.model.vlm),r.model.tokenizer_config&&(o.tokenizer_config=r.model.tokenizer_config),r.model.model_config&&(o.model_config=r.model.model_config),r.runtime.huggingface_token&&(process.env.HF_TOKEN=r.runtime.huggingface_token),await a.bridge.call(`load`,o),t?.(.9);let c=await a.bridge.call(`get_info`);i.modelInfo={model:c.model,peak_memory:c.peak_memory,active_memory:c.active_memory};let u=r.runtime.session_cache;u?.enabled!==!1&&await a.bridge.call(`configure_cache`,{enabled:!0,cache_dir:l.join(e,`mlx-session-cache`),max_entries:u?.max_entries||100,max_size_bytes:mr(u?.max_size_bytes,5*1024*1024*1024)}),a.info.download.exists=!0,t?.(1),H.addModelLoad({id:`load-${Date.now()}`,generatorId:a.id,repoId:r.model.repo_id,variant:`mlx`,durationMs:Date.now()-s,success:!0})})();try{await i.ready}catch(e){throw i.released=!0,a.contexts.delete(o),H.addModelLoad({id:`load-${Date.now()}`,generatorId:a.id,repoId:r.model.repo_id,variant:`mlx`,durationMs:Date.now()-s,success:!1,error:e?.message||String(e)}),e}return{modelInfo:i.modelInfo,runtime:{...a.info.runtime},download:{...a.info.download}}},c=async e=>{if(e.released)return!1;e.released=!0;try{a.bridge?.alive&&await a.bridge.call(`release`)}catch(e){console.error(`[mlx-llm] Error releasing context:`,e.message)}return a.contexts.delete(e.key),!0};return{id:e,type:`mlx-llm`,info:i.info,contexts:a.contexts,queue:a.queue,initContext:s,completion:async(e={})=>{let{options:t={}}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);await n.ready;let r=Mr(t.messages),i=t.prompt||``;if(!i&&t.messages){let e={messages:t.messages,add_generation_prompt:t.add_generation_prompt??!0,tools:t.tools,...t.chat_template_kwargs};t.enable_thinking!=null&&(e.enable_thinking=t.enable_thinking),i=(await a.bridge.call(`apply_chat_template`,e)).text}let s={prompt:i,max_tokens:t.n_predict??t.max_tokens??256};r.length>0&&(s.image=r),t.temperature!=null&&(s.temperature=t.temperature),t.top_p!=null&&(s.top_p=t.top_p),t.top_k!=null&&(s.top_k=t.top_k),t.min_p!=null&&(s.min_p=t.min_p),t.seed!=null&&(s.seed=t.seed),t.repetition_penalty!=null&&(s.repetition_penalty=t.repetition_penalty),t.stop&&(s.stop=t.stop);let c={repoId:a.info.model?.repoId||null},l=`completion-${Date.now()}-${Math.random().toString(36).slice(2,8)}`;return new or({start(e){a.queue.enqueue(async()=>{let n=Ir(a.bridge,s,a.id,c,{enableThinking:!!t.enable_thinking}).getReader();try{for(;;){let{value:t,done:r}=await n.read();if(r)break;e.enqueue(t)}e.close()}catch(t){throw e.error(t),t}},l).catch(t=>{try{e.error(t)}catch{}})},cancel(){a.bridge?.alive}})},tokenize:async(e={})=>{let{text:t=``}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);return await n.ready,a.bridge.call(`tokenize`,{text:t})},detokenize:async(e={})=>{let{tokens:t=[]}=e,n=a.contexts.get(o);if(!n)throw Error(`Context "${o}" not initialized`);return await n.ready,(await a.bridge.call(`detokenize`,{tokens:t})).text},applyChatTemplate:async(e={})=>{let{messages:t=[],params:n={}}=e,r=a.contexts.get(o);if(!r)throw Error(`Context "${o}" not initialized`);await r.ready;let i={messages:t,add_generation_prompt:n.add_generation_prompt??!0,tools:n.tools,...n.chat_template_kwargs};return(await a.bridge.call(`apply_chat_template`,i)).text},releaseContext:async()=>{if(a.finalized)return!1;let e=a.contexts.get(o);if(!e||(e.releaseRequested=!0,e.refCount=Math.max(0,e.refCount-1),e.refCount>0))return!1;let t=r.runtime.context_release_delay_ms??1e4;return t>0?new Promise(n=>{e.releaseTimer=setTimeout(async()=>{e.releaseTimer=null,e.refCount<=0&&!e.released?n(await c(e)):n(!1)},t)}):c(e)},finalize:async()=>{if(a.finalized)return;a.finalized=!0;let e=Array.from(a.contexts.values());for(let t of e)t.released||(t.refCount=0,await c(t));a.bridge?.kill(),a.bridge=null},getStatus:()=>({id:a.id,type:a.type,repoId:a.info.model?.repoId||null,variant:`mlx`,contexts:Array.from(a.contexts.entries()).map(([e,t])=>({key:e,refCount:t.refCount,hasModel:!t.released})),queueStatus:a.queue.getStatus()}),hasPendingReleases:()=>Array.from(a.contexts.values()).some(e=>!e.released&&(e.releaseRequested||e.releaseTimer||e.refCount>0)),resetFinalized:()=>{a.finalized=!1}}}const Rr=e=>gr(e).model.repo_id||null;async function zr(e=null,t={}){let{includeBreakdown:n=!1,config:r}=t,i=Ar(),a=i.length===0,o=!1,s=!1;if(a){try{await q(`python3`,[`--version`],{timeout:5e3}),o=!0}catch{}if(o)try{await q(`python3`,[`-c`,`import mlx`],{timeout:1e4}),s=!0}catch{}}let c=await De({platform:process.platform,arch:x.arch(),totalMemoryInBytes:x.totalmem(),includeBreakdown:n}),l=null,u=null,d=null,f=null,p=null,m=null,h=null;if(r){let e=gr(r),t=e.model.repo_id;if(t)try{l=await Sr(t,{revision:e.model.revision,cacheDir:e.runtime.cache_dir||fr,token:e.runtime.huggingface_token}),u=l.modelBytes||0,f=l.maxCtx||4096;let n={numLayers:l.numLayers,numKvHeads:l.numKvHeads,headDim:l.headDim,isMLA:l.isMLA,kvLoraRank:l.kvLoraRank,qkRopeHeadDim:l.qkRopeHeadDim};d=Cr({...n,contextLength:f});let r=c.ok?c.selected.gpuUsableBytes:0;if(r>0&&u>0&&l.numLayers){let e=r-u;if(e>0){let t;t=l.isMLA&&l.kvLoraRank>0?l.numLayers*(l.kvLoraRank+(l.qkRopeHeadDim||0))*2:l.numKvHeads&&l.headDim?l.numLayers*l.numKvHeads*l.headDim*2*2:0,t>0&&(m=Math.floor(e/t),m=Math.min(m,f))}else m=0;m!=null&&m<f&&(p=Cr({...n,contextLength:m}))}h={repoId:t,revision:e.model.revision,nCtx:f,architecture:l.arch,quantBits:l.quantBits,quantGroupSize:l.quantGroupSize}}catch{}}let g=c.ok?{...c.selected,modelBytes:u,kvCacheBytes:d,memoryLimitedCtx:m,limitedKvCacheBytes:p,kvInfo:l?{nCtxTrain:l.maxCtx||null,nLayer:l.numLayers,nEmbd:l.hiddenSize,nHeadKv:l.numKvHeads,headDim:l.headDim}:null,quantization:l?{bits:l.quantBits,groupSize:l.quantGroupSize,dtype:l.dtype}:null}:null;if(c.ok&&u!=null&&u>0){let e=u+(d||0),t=c.selected.gpuUsableBytes,n=e<=t;if(g.fit={totalRequiredBytes:e,fitsInGpu:n,fitsInCpu:e<=t,limiting:n?`none`:`insufficient-memory`},p!=null&&p!==d){let e=u+p;g.limitedFit={totalRequiredBytes:e,fitsInGpu:e<=t,fitsInCpu:e<=t,limiting:e<=t?`none`:`insufficient-memory`}}}return{type:`mlx-llm`,available:a,platform:{ok:a,os:process.platform,arch:x.arch(),errors:i},python:{available:o},mlx:{systemAvailable:s,venvSupported:o},buttress:c.ok?{ok:c.ok,selected:g,attempts:c.attempts}:{ok:!1,selected:null,attempts:c.attempts||[],errors:c.errors},modelConfig:h,timestamp:new Date().toISOString()}}async function Br(e,t,n={}){let{onProgress:r,onComplete:i,onError:a}=n,o=gr(e),s=o.model.repo_id;if(!s)return{started:!1,localPath:null,repoId:null,error:`Missing repo_id`};let c=Ar();if(c.length>0)return{started:!1,localPath:null,repoId:s,error:c.join(`; `)};let u=`mlx:${s}`;if(t?.isDownloading(u))return{started:!1,localPath:null,repoId:s,alreadyDownloading:!0};let d=(async()=>{try{let e=o.runtime.cache_dir||fr,t=await Er({envDir:o.runtime.mlx_env_dir||l.join(e,`mlx-env`),mlxLmPackage:o.runtime.mlx_lm_package||dr,mlxVlmPackage:o.runtime.mlx_vlm_package||ur,onProgress:r?e=>r(e*.3):void 0});r?.(.3);let n=`
 from huggingface_hub import snapshot_download
 path = snapshot_download("${s}", revision="${o.model.revision||`main`}")
 print(path)
 `.trim(),a={...process.env};o.runtime.huggingface_token&&(a.HF_TOKEN=o.runtime.huggingface_token);let c=await q(t,[`-c`,n],{timeout:6e5,env:a});r?.(1);let u=c.stdout.trim().split(`
-`).pop();i?.({localPath:u,repoId:s,alreadyExists:!1})}catch(e){throw a?.(e),e}finally{t?.deleteDownload(u)}})();return t?.setDownload(u,d),{started:!0,localPath:null,repoId:s}}async function J(e,t=null,n={}){if(e===`ggml-llm`)return vn(t,n);if(e===`ggml-stt`)return ar(t,n);if(e===`mlx-llm`)return zr(t,n);throw Error(`Unknown backend type: ${e}`)}var Y=`@fugood/buttress-backend-core`,X=`2.24.1`,Vr={name:Y,private:!0,type:`module`,version:X,main:`src/index.js`,types:`lib/types/index.d.ts`,scripts:{build:`tsc --noCheck --declaration --emitDeclarationOnly --allowJs --outDir lib/types src/index.js`},dependencies:{"@fugood/buttress-hardware-guardrails":`^2.24.0`,"@fugood/llama.node":`^1.7.3`,"@fugood/whisper.node":`^1.0.19`,"@huggingface/gguf":`^0.3.2`,"@iarna/toml":`^3.0.0`,bytes:`^3.1.0`}};const Hr=e=>{if(!e)return{repoId:null,filename:null};let[t,n]=e.split(`:`);return{repoId:t,filename:n||null}};async function Ur({modelIds:e=[],defaultConfig:t=null}={}){let n=[];console.log(`${Y} v${X}`),console.log(`Generating model capabilities comparison...
+`).pop();i?.({localPath:u,repoId:s,alreadyExists:!1})}catch(e){throw a?.(e),e}finally{t?.deleteDownload(u)}})();return t?.setDownload(u,d),{started:!0,localPath:null,repoId:s}}async function J(e,t=null,n={}){if(e===`ggml-llm`)return vn(t,n);if(e===`ggml-stt`)return ar(t,n);if(e===`mlx-llm`)return zr(t,n);throw Error(`Unknown backend type: ${e}`)}var Y=`@fugood/buttress-backend-core`,X=`2.24.1`,Vr={name:Y,private:!0,type:`module`,version:X,main:`src/index.js`,types:`lib/types/index.d.ts`,scripts:{build:`tsc --noCheck --declaration --emitDeclarationOnly --allowJs --outDir lib/types src/index.js`},dependencies:{"@fugood/buttress-hardware-guardrails":`^2.24.0`,"@fugood/llama.node":`^1.7.4`,"@fugood/whisper.node":`^1.0.19`,"@huggingface/gguf":`^0.3.2`,"@iarna/toml":`^3.0.0`,bytes:`^3.1.0`}};const Hr=e=>{if(!e)return{repoId:null,filename:null};let[t,n]=e.split(`:`);return{repoId:t,filename:n||null}};async function Ur({modelIds:e=[],defaultConfig:t=null}={}){let n=[];console.log(`${Y} v${X}`),console.log(`Generating model capabilities comparison...
 `),n.push(`${Y} v${X}`),n.push(`## Model Capabilities Comparison
 `),(!e||e.length===0)&&(console.error(`Error: No model IDs provided`),process.exit(1));try{let r=(e={},t={})=>{let n=Array.isArray(e)?[...e]:{...e};return Object.entries(t||{}).forEach(([e,t])=>{t&&typeof t==`object`&&!Array.isArray(t)?n[e]=r(n[e]||{},t):n[e]=t}),n},{server:i,generators:a=[],...o}=t||{},s=e=>r(structuredClone(o),e||{}),c=e=>{if(Array.isArray(a)&&a.length>0){let t=a.filter(e=>e?.type===`ggml-llm`);if(t.length>0&&e){let n=t.find(t=>t.model?.repo_id===e);if(n)return s(n)}}return Object.keys(o).length>0?s({}):null},u=[];for(let t=0;t<e.length;t+=1){let n=e[t];console.log(`[${t+1}/${e.length}] Analyzing ${n}...`);let r=c(n);r={...r||{},model:{...o.runtime,...r?.model||{},repo_id:n}};let i=await J(`ggml-llm`,null,{config:r,includeBreakdown:!0});u.push({modelId:n,capabilities:i,modelInfo:i.buttress?.selected||null,modelConfig:i.modelConfig||null})}let d=e=>e?(e/1024/1024/1024).toFixed(2):`N/A`,f=e=>e?`✅`:`🚫`;n.push(`| Model ID | Quantization | Size (GB) | Context Size | KV Cache Size (GB) | Total Required Memory (GB) | Fits GPU (Full) | Fits CPU (Full) |`),n.push(`|----------|--------------|-----------|--------------|--------------------|-----------------------------|-----------------|-----------------|`),u.forEach(({modelId:e,modelInfo:t,modelConfig:r})=>{let i=t?.quantization?.name?.toUpperCase()||`N/A`,a=d(t?.modelBytes),o=r?.nCtx||t?.kvInfo?.nCtxTrain||`N/A`,s=qe(t),c=Number(o),l=t?.kvCacheBytes||(s&&Number.isFinite(c)&&c>0?s(c):s&&s(t?.kvInfo?.nCtxTrain||0))||null,u=d(l),p=d(t?.modelBytes&&l?t.modelBytes+l:t?.fit?.totalRequiredBytes),m=f(t?.fit?.fitsInGpu),h=f(t?.fit?.fitsInCpu);n.push(`| ${e} | ${i} | ${a} | ${o} | ${u} | ${p} | ${m} | ${h} |`);let g=t?.memoryLimitedCtx!=null||t?.limitedFit!=null,_=!t?.fit?.fitsInGpu||!t?.fit?.fitsInCpu;if(g&&_){let e=t?.memoryLimitedCtx||o,r=Number(e),i=t?.limitedKvCacheBytes||s&&Number.isFinite(r)&&r>0&&s(r)||null,c=d(i),l=d(t?.modelBytes&&i?t.modelBytes+i:t?.limitedFit?.totalRequiredBytes),m=f(t?.limitedFit?.fitsInGpu),h=f(t?.limitedFit?.fitsInCpu);(e!==o||c!==u||l!==p)&&n.push(`| ↳ Limited | - | ${a} | ${e} | ${c} | ${l} | ${m} | ${h} |`)}}),n.push(`
 ---`),n.push(`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fugood/buttress-server",
-  "version": "2.24.5",
+  "version": "2.24.6",
   "main": "lib/index.mjs",
   "types": "lib/index.d.mts",
   "type": "module",
@@ -30,7 +30,7 @@
   "dependencies": {
     "@elysiajs/cors": "^1.1.1",
     "@elysiajs/node": "^1.4.2",
-    "@fugood/llama.node": "^1.7.3",
+    "@fugood/llama.node": "^1.7.4",
     "@fugood/whisper.node": "^1.0.19",
     "@huggingface/gguf": "^0.3.2",
     "@iarna/toml": "^3.0.0",