From 503eb703590e712b9a351545b726265b4c1e681b Mon Sep 17 00:00:00 2001
From: gamer147 <gamer147@gmail.com>
Date: Mon, 6 Jul 2026 13:01:20 -0400
Subject: [PATCH] feat(opcodes): linter (dangling-ref, confidence-ceiling,
 vocabulary)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 tools/opcodes_model.py | 29 +++++++++++++++++++++
 tools/test_opcodes.py  | 59 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)

diff --git a/tools/opcodes_model.py b/tools/opcodes_model.py
index 26d18f4..d6ea358 100644
--- a/tools/opcodes_model.py
+++ b/tools/opcodes_model.py
@@ -67,6 +67,35 @@ def load(path) -> Model:
         )
     return Model(meta=data.get("meta", {}), opcodes=ops)
 
+def lint(model: Model) -> tuple[list[str], list[str]]:
+    """Return (errors, warnings). Errors: bad vocabulary, dangling depends_on.
+    Warnings: confidence exceeds the minimum confidence among its dependencies."""
+    errors: list[str] = []
+    warnings: list[str] = []
+    ops = model.opcodes
+    for op, oc in sorted(ops.items()):
+        s = oc.semantics
+        if not s:
+            continue
+        tag = f"0x{op:x}"
+        if s.category not in CATEGORIES:
+            errors.append(f"{tag}: bad category {s.category!r}")
+        if s.source not in SOURCES:
+            errors.append(f"{tag}: bad source {s.source!r}")
+        if s.confidence not in CONFIDENCE:
+            errors.append(f"{tag}: bad confidence {s.confidence!r}")
+        for dep in s.depends_on:
+            if dep not in ops:
+                errors.append(f"{tag}: depends_on missing opcode 0x{dep:x}")
+        if s.confidence in CONFIDENCE:
+            dep_confs = [CONFIDENCE[ops[d].semantics.confidence]
+                         for d in s.depends_on
+                         if d in ops and ops[d].semantics
+                         and ops[d].semantics.confidence in CONFIDENCE]
+            if dep_confs and CONFIDENCE[s.confidence] > min(dep_confs):
+                warnings.append(f"{tag}: confidence {s.confidence!r} exceeds dependency ceiling")
+    return errors, warnings
+
 def dependents(model: Model) -> dict[int, list[int]]:
     """Reverse of depends_on: op -> [ops whose semantics depend on it]."""
     rev: dict[int, list[int]] = {op: [] for op in model.opcodes}
diff --git a/tools/test_opcodes.py b/tools/test_opcodes.py
index b67befe..3c186de 100644
--- a/tools/test_opcodes.py
+++ b/tools/test_opcodes.py
@@ -58,8 +58,67 @@ def test_load():
     rev = M.dependents(m)
     check(rev.get(0x1f4) == [0x90], "dependents: 0x1f4 depended on by 0x90")
 
+DANGLING = '''
+[[opcode]]
+op = 0x10
+label = "x"
+argc = 0
+[opcode.semantics]
+name = "a"
+category = "compute"
+source = "inference"
+confidence = "low"
+depends_on = [0x99]
+'''
+
+CEILING = '''
+[[opcode]]
+op = 0x10
+label = "x"
+argc = 0
+[opcode.semantics]
+name = "low-op"
+category = "compute"
+source = "kelebek"
+confidence = "low"
+[[opcode]]
+op = 0x11
+label = "y"
+argc = 0
+[opcode.semantics]
+name = "high-op"
+category = "compute"
+source = "inference"
+confidence = "high"
+depends_on = [0x10]
+'''
+
+BADVOCAB = '''
+[[opcode]]
+op = 0x10
+label = "x"
+argc = 0
+[opcode.semantics]
+name = "a"
+category = "bogus"
+source = "inference"
+confidence = "low"
+'''
+
+def test_lint():
+    e, w = M.lint(M.load(write_tmp(DANGLING)))
+    check(any("0x99" in m for m in e), "dangling depends_on is an error")
+    e, w = M.lint(M.load(write_tmp(CEILING)))
+    check(any("0x11" in m for m in w), "confidence-ceiling violation is a warning")
+    check(e == [], "confidence-ceiling case has no errors")
+    e, w = M.lint(M.load(write_tmp(BADVOCAB)))
+    check(any("category" in m for m in e), "unknown category is an error")
+    e, w = M.lint(M.load(write_tmp(FIXTURE)))
+    check(e == [], "clean fixture has no lint errors")
+
 def main():
     test_load()
+    test_lint()
     print("FAILURES:", len(FAILS))
     return 1 if FAILS else 0