feat(plane): budget metering (task 2)

MeteredClient wraps a ChatClient, sums the provider's usage rows per call,
prices them from a Model manifest's parameters (cache-hit, input, output per
million), and raises BudgetExhausted before a call once the usd or calls
ceiling is reached. A 401/402 or "Insufficient Balance" failure becomes
AccountError with the provider's message. An unpriced model reports usd None,
never zero, and refuses a usd budget; summary() gives the spend block of a
task's summary.json.

The two plane modules are registered as spec-owned in the module audit (their
consumers land in tasks 3-4) and the audit manifest is regenerated.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

benchmarks/measurements/2026-09-08-module-audit.json

@@ -1,7 +1,7 @@
 {
-  "modules": 118,
+  "modules": 120,
   "counts": {
-    "load_bearing": 109,
+    "load_bearing": 111,
     "standalone_capability": 9
   },
   "orphaned": [],
@@ -400,6 +400,7 @@
         "model.scan",
         "model.specs",
         "model.taint",
+        "plane.budget",
         "preprocess",
         "push.assistance",
         "push.cache",
@@ -409,7 +410,8 @@
         "push.reuse",
         "push.runner",
         "push.snapshot",
-        "push.vetoes"
+        "push.vetoes",
+        "tool_hunter"
       ]
     },
     {
@@ -479,7 +481,9 @@
       "reason": "model-grounded-detection Req 8: the judge client, wired by model/judge.py in group 3",
       "importers": [
         "cli",
-        "push.assistance"
+        "plane.budget",
+        "push.assistance",
+        "tool_hunter"
       ]
     },
     {
@@ -645,6 +649,18 @@
         "pair_gate"
       ]
     },
+    {
+      "module": "plane",
+      "classification": "load_bearing",
+      "reason": "ai-service-plane Req 1-4: the service plane package; runner and reconciler integration in tasks 3-4",
+      "importers": []
+    },
+    {
+      "module": "plane.budget",
+      "classification": "load_bearing",
+      "reason": "ai-service-plane Req 2.3/2.4: metered chat client with usd and calls ceilings; task integration in tasks 3, 6",
+      "importers": []
+    },
     {
       "module": "policy",
       "classification": "load_bearing",
@@ -1041,6 +1057,7 @@
         "mapping",
         "model.candidates",
         "model.layout",
+        "model.scan",
         "model.specs",
         "pairs",
         "semantic.cst",
@@ -1048,6 +1065,7 @@
         "semantic.functions",
         "semantic.ir",
         "semantic.obligations.check",
+        "semantic.obligations.facts",
         "semantic.obligations.operations",
         "semantic.obligations.shapes",
         "semantic.overlay",
@@ -1093,10 +1111,12 @@
         "mapping",
         "model.candidates",
         "model.layout",
+        "model.scan",
         "model.specs",
         "pairs",
         "semantic",
         "semantic.obligations.check",
+        "semantic.obligations.facts",
         "semantic.obligations.operations",
         "semantic.obligations.shapes",
         "semantic.overlay",
@@ -1293,7 +1313,8 @@
       "classification": "load_bearing",
       "reason": "reachable from gate, map_gate, pair_gate or the CLI",
       "importers": [
-        "model.endpoint"
+        "model.endpoint",
+        "plane.budget"
       ]
     },
     {