feat: let admins manage model placement

packages/tracker/meshnet_tracker/server.py

@@ -1528,6 +1528,49 @@ def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) ->
     return None
 
 
+def _force_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> dict | None:
+    """Replace the fastest ready assignment after an explicit admin eviction."""
+    resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
+    if preset is None or not preset.get("hf_repo"):
+        return None
+    start, end = _preset_layer_bounds(preset)
+    candidates = [node for node in server.registry.values()
+                  if node.status == "ready" and node.pending_new_assignment is None
+                  and _has_usable_quantization(node)]
+    if not candidates:
+        return None
+    node = max(candidates, key=lambda item: item.benchmark_tokens_per_sec)
+    shard_end = min(end, start + min(_node_layer_capacity(node, preset), end - start + 1) - 1)
+    if shard_end < start:
+        return None
+    quantization = _node_quantization(node, preset)
+    directive = _load_directive(node, str(preset["hf_repo"]), start, shard_end, quantization)
+    replaced = node.hf_repo or node.model
+    node.model, node.hf_repo = resolved_name, str(preset["hf_repo"])
+    node.shard_start, node.shard_end, node.quantization = start, shard_end, quantization
+    node.managed_assignment, node.pending_new_assignment = True, directive
+    node.pending_directives.append(directive)
+    _tracker_log(server, "warn", "model load forced", node_id=node.node_id,
+                 model=resolved_name, replaced_model=replaced, shard=f"{start}-{shard_end}")
+    return {"node_id": node.node_id, "model": resolved_name, "hf_repo": preset["hf_repo"],
+            "shard_start": start, "shard_end": shard_end, "replaced_model": replaced}
+
+
+def _release_model_locked(server: "_TrackerHTTPServer", model_key: str) -> int:
+    """Queue DROP_SHARD for every served shard and remove it from routing immediately."""
+    resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
+    if preset is None:
+        return 0
+    released = 0
+    for node in server.registry.values():
+        if not _node_matches_preset(node, resolved_name, preset) or node.shard_start is None or node.shard_end is None:
+            continue
+        node.pending_directives.append(_drop_directive(node, str(preset.get("hf_repo") or resolved_name), node.shard_start, node.shard_end, node.quantization or "bfloat16"))
+        node.status = "loading"
+        released += 1
+    return released
+
+
 def _preferred_node_quantization(
     node: _NodeEntry,
     preset: dict,
@@ -3043,6 +3086,9 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         if self.path == "/v1/models/load":
             self._handle_model_load_request()
             return
+        if self.path == "/v1/models/release":
+            self._handle_model_release_request()
+            return
         if self.path == "/v1/models/vote":
             self._handle_model_coverage_vote()
             return
@@ -3170,8 +3216,6 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         seen_ids: set[str] = set()
         for name, preset in server.model_presets.items():
             model_nodes = [node for node in alive if _node_matches_preset(node, name, preset)]
-            if not model_nodes and not preset.get("recommended"):
-                continue
             required_start, required_end = _preset_layer_bounds(preset)
             coverage = _coverage_percentage(
                 model_nodes,
@@ -4834,11 +4878,32 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         with server.lock:
             self._purge_expired_nodes()
             assignment = _request_model_load_locked(server, model)
+            if assignment is None and body.get("force") is True:
+                assignment = _force_model_load_locked(server, model)
         if assignment is None:
             self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
             return
         self._send_json(202, {"status": "queued", "assignment": assignment})
 
+    def _handle_model_release_request(self):
+        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
+        if not self._require_role("admin", "validator"):
+            return
+        body = self._read_json_body()
+        if body is None:
+            return
+        model = body.get("model")
+        if not isinstance(model, str) or not model.strip():
+            self._send_json(400, {"error": "model is required"})
+            return
+        with server.lock:
+            self._purge_expired_nodes()
+            released = _release_model_locked(server, model)
+        if not released:
+            self._send_json(404, {"error": "no served shards found for model"})
+            return
+        self._send_json(202, {"status": "release_queued", "released": released})
+
     def _handle_model_coverage_vote(self):
         """Record a rolling wish-list signal for an unavailable precision."""
         server: _TrackerHTTPServer = self.server  # type: ignore[assignment]