Your own bankML in one command: ./install.sh --space (github main a27c4b6)

CHANGELOG.md

@@ -31,7 +31,8 @@ decode speed, the third, is measured on an idle machine next.
 - `bankml serve … --allow-origin ORIGIN` lets one named web page call the gateway from a browser: its CORS preflight
   is answered (with Chrome's private-network grant, as a public page reaching a loopback address requires) and its
   answers, streamed or not, carry `Access-Control-Allow-Origin`; any other origin gets none and a 403 preflight. The
-  loopback `Host` and JSON-POST rules are unchanged. It is what lets the bankML Space's page
+  loopback `Host` and JSON-POST rules are unchanged. `./install.sh start --space` turns it on for the Space (remembered
+  in `install.env`, applied to the carrier `sAGI/models.py` starts; `--no-space` turns it off). It is what lets the bankML Space's page
   ([PYTHAI/bankml](https://huggingface.co/spaces/PYTHAI/bankml)) talk to a visitor's own bankML, free, on their own
   CPU — the way Savante's page reaches a local engine. Checked live: the preflight, plain and streamed answers with
   the receipt, and another origin refused.

docs/install.md

@@ -135,6 +135,7 @@ alone brings the whole stack back. Use `./install.sh model start` to wait for th
 | `--no-start` | the default run ends after `model` (or `voice`): everything installed, Savante not started. `bankml serve` is still started by `model` |
 | `--view` | `start` also starts view mode on `0.0.0.0:7874`. It works with named steps too: `./install.sh start --view` |
 | `--voice` | the default run includes `voice`. With named steps, name it instead: `./install.sh voice` |
+| `--space` / `--no-space` | 0.3.9: let bankML's Hugging Face page ([PYTHAI/bankml](https://huggingface.co/spaces/PYTHAI/bankml)) talk to your `bankml serve` from your browser — its *Your own bankML* mode: your CPU, your verified model, a receipt the page checks. Serve starts with `--allow-origin https://pythai-bankml.static.hf.space` (that one page, nothing else); the choice is remembered in `install.env` (`INSTALL_ALLOW_ORIGIN`; `BANKML_ALLOW_ORIGIN` overrides it). `./install.sh start --space` applies it at once (the running services stop first); `--no-space` forgets it. `./install.sh status` says which page is allowed |
 | `-h`, `--help` | prints the header of `install.sh` and exits |
 
 Any other argument stops the installer with exit code 2.

docs/usage.md

@@ -247,9 +247,11 @@ In the next release (not yet tagged); each is checked against llama-server b1119
   llama-server `-np 1`. Like llama-server, it keeps the states of other conversations in RAM (`BANKML_CACHE_RAM`, MiB;
   0 off, -1 no limit; unset, 8192 MiB but at most a quarter of the memory available at load), so a conversation that comes back after
   another does not recompute its whole history.
-- **Your bankML from a web page (0.3.9).** `--allow-origin https://pythai-bankml.static.hf.space` lets the bankML
-  Space's page talk to your own `bankml serve` from your browser: your CPU, your verified model, a receipt on every
-  answer, nothing sent anywhere else. Only that one origin is answered with CORS headers.
+- **Your bankML from a web page (0.3.9).** `./install.sh start --space` lets the bankML Space's page
+  ([PYTHAI/bankml](https://huggingface.co/spaces/PYTHAI/bankml), *Your own bankML*) talk to your own `bankml serve`
+  from your browser: your CPU, your verified model, a receipt on every answer, nothing sent anywhere else. It starts
+  serve with `--allow-origin https://pythai-bankml.static.hf.space`, so only that one page gets CORS headers;
+  `./install.sh start --no-space` takes it back.
 - **A smaller conversation memory (0.3.9, in progress).** `BANKML_CACHE_TYPE=q8_0` keeps the KV cache in q8_0 instead of f16,
   about half the memory, so a long context fits on a small machine. It is llama.cpp's `--cache-type-k q8_0
   --cache-type-v q8_0` exactly, with the Hadamard rotation llama.cpp applies around a quantized cache, and gives the

index.html

@@ -184,10 +184,12 @@
         <details>
           <summary>Start your own bankML for this page (Linux, AVX2; free)</summary>
           <ol>
-            <li><code>git clone https://github.com/cryptoAGI/bankml &amp;&amp; cd bankml &amp;&amp; ./install.sh</code> — builds bankML and imports and verifies Bonsai-8B.</li>
-            <li><code>./install.sh stop</code> (the installer's own serve does not allow web pages), then:<br>
-              <code>target/release/bankml serve .models/Bonsai-8B-Q1_0.gguf --fork ~/.local/share/bankml/forks/Bonsai-8B-Q1_0.gguf.FORK.json --native --allow-origin <span id="origin"></span></code></li>
-            <li>Press <b>connect</b>. Your browser may ask to let this page reach your machine: that is the request for your own bankML on 127.0.0.1, and nothing else.</li>
+            <li><code>git clone https://github.com/cryptoAGI/bankml &amp;&amp; cd bankml &amp;&amp; ./install.sh --space</code> — builds bankML,
+              imports and verifies Bonsai-8B, and starts it so this page (<span id="origin"></span>) may talk to it. Already installed?
+              <code>git pull &amp;&amp; ./install.sh build start --space</code></li>
+            <li>Press <b>connect</b>. Your browser may ask to let this page reach devices on your local network: that is the
+              request for your own bankML on 127.0.0.1, and nothing else.</li>
+            <li><code>./install.sh start --no-space</code> takes the permission back.</li>
           </ol>
         </details>
       </div>

install.sh

@@ -11,6 +11,10 @@
 #   --no-start     install everything, start nothing
 #   --view         also start view mode for the LAN (0.0.0.0:7874)
 #   --voice        also install Savante's Piper voice (step `voice`)
+#   --space        let bankML's Hugging Face page (huggingface.co/spaces/PYTHAI/bankml) talk to your bankml serve from
+#                  your browser ("Your own bankML": your CPU, your verified model, a receipt): serve starts with
+#                  --allow-origin for that one page; remembered; `./install.sh start --space` applies it now
+#   --no-space     forget it (serve answers this computer only, no web page)
 #   power [--remove]  opt-in, sudo: let your user read the CPU package energy counter (RAPL), so bankML can measure
 #                  watts and joules per token; it asks first (PLATYPUS, CVE-2020-8694), and --remove undoes it
 #   -h, --help     this text
@@ -72,7 +76,9 @@ else CANON="$HOME/cryptoAGI/savante"; fi
 LOGS="$DATA/logs"
 
 # ── options ──────────────────────────────────────────────────────────────────────────────────────────────────
-SKIP_TESTS=0 NO_START=0 WITH_VIEW=0 WITH_VOICE=0 POWER_REMOVE=0
+SKIP_TESTS=0 NO_START=0 WITH_VIEW=0 WITH_VOICE=0 POWER_REMOVE=0 SPACE_CHOICE=""
+# the one web page --space lets reach bankml serve: bankML's static Hugging Face Space
+SPACE_ORIGIN="https://pythai-bankml.static.hf.space"
 STEPS=()
 for a in "$@"; do
   case "$a" in
@@ -81,7 +87,9 @@ for a in "$@"; do
     --view)       WITH_VIEW=1;;
     --voice)      WITH_VOICE=1;;
     --remove)     POWER_REMOVE=1;;
-    -h|--help)    sed -n '3,19p' "$HERE/install.sh" | sed 's/^# \{0,1\}//'; exit 0;;
+    --space)      SPACE_CHOICE=on;;
+    --no-space)   SPACE_CHOICE=off;;
+    -h|--help)    sed -n '3,21p' "$HERE/install.sh" | sed 's/^# \{0,1\}//'; exit 0;;
     check|build|engine|python|canon|model|voice|start|stop|status|power) STEPS+=("$a");;
     *) bm_die "unknown argument: $a (see ./install.sh --help)" 2;;
   esac
@@ -103,6 +111,13 @@ save_env() {  # save_env KEY VALUE: remember a choice in $ENV_FILE
 }
 # shellcheck disable=SC1090
 [ -f "$ENV_FILE" ] && . "$ENV_FILE"
+# --space / --no-space: remembered for sAGI/models.py, which starts serve; given with `start`, the running services
+# stop first, so the carrier comes back with (or without) --allow-origin
+if [ -n "$SPACE_CHOICE" ]; then
+  if [ "$SPACE_CHOICE" = on ]; then INSTALL_ALLOW_ORIGIN="$SPACE_ORIGIN"; else INSTALL_ALLOW_ORIGIN=""; fi
+  save_env INSTALL_ALLOW_ORIGIN "$INSTALL_ALLOW_ORIGIN"
+  if printf '%s\n' "${STEPS[@]}" | grep -qx start && ! printf '%s\n' "${STEPS[@]}" | grep -qx stop; then STEPS=(stop "${STEPS[@]}"); fi
+fi
 sha256_of() { if have sha256sum; then sha256sum "$1" | cut -d' ' -f1; else shasum -a 256 "$1" | cut -d' ' -f1; fi; }
 fetch() {  # fetch URL FILE: resumable download
   local bar=--silent; [ -t 2 ] && bar=--progress-bar
@@ -281,6 +296,9 @@ step_start() {
   bm_sub "talk:   $(bm_link http://127.0.0.1:7873)   (this computer only)"
   [ "$WITH_VIEW" = 1 ] && bm_sub "watch:  http://<this computer's LAN address>:7874"
   bm_sub "check:  curl -s 127.0.0.1:18093/bankml"
+  if [ -n "${INSTALL_ALLOW_ORIGIN:-}" ]; then
+    bm_sub "web:    huggingface.co/spaces/PYTHAI/bankml → \"Your own bankML\" reaches this bankml serve (./install.sh start --no-space to stop it)"
+  fi
   bm_sub "docs:   $(bm_link https://cryptoagi.github.io/bankml/)"
 }
 
@@ -310,6 +328,7 @@ print("   verified:", s.get("verified"), "·", s.get("model", "?").rsplit("/", 1
 PY
   fi
   [ -x "$BIN" ] && bm_info "$("$BIN" version)"
+  bm_info "web page allowed (--space): ${INSTALL_ALLOW_ORIGIN:-none — this computer only}"
   bm_info "engine: ${LLAMA_SERVER:-not installed} · python: $PY"
 }
 

sAGI/models.py

@@ -661,6 +661,15 @@ def usage() -> dict:
             "mem_total_gb": round(mem_total() / 1e9, 1), "mem_available_gb": round(avail / 1e9, 2), "source": "sAGI/models.py (/proc)"}
 
 
+def allow_origin() -> str | None:
+    """The one web page bankml serve lets in (`--allow-origin`): BANKML_ALLOW_ORIGIN, else what `./install.sh --space`
+    recorded; None (this computer only) when neither is set."""
+    o = os.environ.get("BANKML_ALLOW_ORIGIN")
+    if o is None:
+        o = _install_env(DATA).get("INSTALL_ALLOW_ORIGIN", "")
+    return o.strip() or None
+
+
 def native_for(model: Path, engine: str | None = None) -> bool:
     """Whether the carrier answers from bankML's own forward pass (`bankml serve --native`, 0.3.0) for this model:
     "native" always (bankml refuses a model its forward pass does not run), "llama.cpp" never, "auto" for the
@@ -734,6 +743,9 @@ def _start_carrier(model: Path, fork: Path, want_sha: str | None = None, threads
             cmd = ([str(BANKML), "serve", str(model), "--fork", str(fork), "--spawn", str(LLAMA), "--upstream", UPSTREAM, "--listen", LISTEN,
                     "--threads", n_threads, "--ctx", n_ctx] + (["--spec-ngram"] if resources().get("spec_ngram") else []) + ["--slot-dir", str(SLOTS)])
             env = None
+        if allow_origin():
+            # ./install.sh --space: bankML's Hugging Face page may talk to this serve from the browser (CORS for it alone)
+            cmd += ["--allow-origin", allow_origin()]
         proc = subprocess.Popen(cmd, stdout=log, stderr=log, stdin=subprocess.DEVNULL, start_new_session=True, cwd=str(REPO), env=env)
     t0 = time.time()
     why = "timed out"  # ctx: per model — the saved RAM budget is re-planned for this model's weights and KV size