feat(learn): the classifier program and its response cache (decision-engine 6.4)

learn/program.py: the declared signature (code, signals, roles, family in;
verdict, family, confidence, rationale with cited lines out), the
baseline instruction, rendering as [system: instruction + demonstrations]
-- byte-identical for every candidate, so the provider's prefix cache can
hit -- then [user: retrieved examples with their labels, the candidate
without one]. Signals pass validate_x first (no EXCLUDED_FIELDS, missing
instruments in words). Answers are one JSON object; one that does not
parse or cites no line inside the excerpt is asked once more at
temperature 0 and otherwise becomes unsure/parse_failed, never
not_vulnerable. Classify(k): sample 1 at 0.0, the rest at 0.7; score s =
mean p_j; majority verdict, ties unsure; a majority unsure cannot BLOCK.
Caller caches each response as responses/<sha>.json keyed by (model,
Model parameters digest, messages, temperature, sample, json_object) and
replays at $0; spend is priced from the recorded usage once per distinct
request, so a replay reports the same usd. Program.decide asserts the
evaluation boundary on the rendered ids before any call.

MeteredClient.complete passes temperature/logprobs through (only when
set); DeepSeekChatClient sends temperature beside thinking=disabled.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

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

@@ -1,7 +1,7 @@
 {
-  "modules": 149,
+  "modules": 150,
   "counts": {
-    "load_bearing": 142,
+    "load_bearing": 143,
     "standalone_capability": 7
   },
   "orphaned": [],
@@ -358,6 +358,7 @@
         "learn.excerpt",
         "learn.features",
         "learn.folds",
+        "learn.program",
         "learn.retrieve",
         "learn.roles",
         "plane.tasks.features",
@@ -389,6 +390,7 @@
       "importers": [
         "learn.cli",
         "learn.folds",
+        "learn.program",
         "learn.retrieve"
       ]
     },
@@ -413,8 +415,9 @@
     {
       "module": "learn.folds",
       "classification": "load_bearing",
-      "reason": "imported by learn.retrieve",
+      "reason": "imported by learn.program, learn.retrieve",
       "importers": [
+        "learn.program",
         "learn.retrieve"
       ]
     },
@@ -430,11 +433,19 @@
         "learn.retrieve"
       ]
     },
+    {
+      "module": "learn.program",
+      "classification": "load_bearing",
+      "reason": "learned-decision-engine Req 3.1/3.3: the AI classifier program (signature, Retrieve -> Classify(k), response cache); `ousast learn compile` (task 6.5) and the decide task (task 8) are its callers",
+      "importers": []
+    },
     {
       "module": "learn.retrieve",
       "classification": "load_bearing",
-      "reason": "learned-decision-engine Req 3.2/3.4: retrieval from the local memory and the evaluation boundary; the program (task 6.4) and `ousast learn compile` (6.5) are its callers",
-      "importers": []
+      "reason": "imported by learn.program",
+      "importers": [
+        "learn.program"
+      ]
     },
     {
       "module": "learn.roles",
@@ -452,6 +463,7 @@
       "reason": "reachable from gate, map_gate, pair_gate or the CLI",
       "importers": [
         "learn.features",
+        "learn.program",
         "learn.retrieve",
         "learn.roles",
         "plane.tasks.remember",
@@ -785,6 +797,7 @@
         "learn.cli",
         "learn.embeddings",
         "learn.examples",
+        "learn.program",
         "plane.egress",
         "plane.engine_alerts",
         "plane.generate",
@@ -806,6 +819,7 @@
       "importers": [
         "learn.cli",
         "learn.embeddings",
+        "learn.program",
         "plane.generate",
         "plane.tasks.roles",
         "plane.tasks.verify"
@@ -864,6 +878,7 @@
         "learn.cli",
         "learn.embeddings",
         "learn.examples",
+        "learn.program",
         "plane.generate",
         "plane.tasks.loop",
         "plane.tasks.remember"
@@ -1073,6 +1088,7 @@
       "reason": "reachable from gate, map_gate, pair_gate or the CLI",
       "importers": [
         "learn.cli",
+        "learn.program",
         "model.endpoint",
         "tool_hunter"
       ]
@@ -1083,6 +1099,7 @@
       "reason": "reachable from gate, map_gate, pair_gate or the CLI",
       "importers": [
         "learn.cli",
+        "learn.program",
         "model.endpoint",
         "tool_hunter"
       ]