Add 89 new tree-sitter grammars (66 to 155 languages)

Vendor, wire up, and compile 89 new tree-sitter grammars, expanding
language support from 66 to 155 languages. All grammars pass security
audit (no dangerous patterns in scanner.c files).

New programming languages (31):
  Solidity, Typst, GDScript, Gleam, PowerShell, Pascal, D, Nim, Scheme,
  Fennel, Fish, AWK, Zsh, Tcl, Ada, Agda, Racket, Odin, ReScript,
  PureScript, Nickel, Crystal, Teal, Hare, Pony, Luau, Janet, Sway,
  NASM, Assembly, TLA+, Pkl, Cairo, Move, Squirrel, ISPC, FunC, Smali

New config/data/IDL formats (31):
  Just, Astro, Blade, Go Template, Templ, Liquid, Jinja2, Prisma,
  Hyprlang, DotEnv, Diff, WGSL, KDL, JSON5, Jsonnet, RON, Thrift,
  Cap'n Proto, Properties, SSH Config, BibTeX, Starlark, Bicep, CSV,
  Requirements, HLSL, VHDL, SystemVerilog, DeviceTree, Linker Script,
  GN, Kconfig, BitBake, TableGen, Slang, LLVM IR, Smithy, WIT,
  Go Mod, Mermaid, RST, Beancount, Puppet, PO, Regex, JSDoc,
  gitattributes, gitignore, Apex, SOQL, SOSL

Infrastructure:
  - scripts/new-languages.json: manifest for all new languages
  - scripts/generate-lang-code.py: generates boilerplate from manifest
  - scripts/audit-grammar-security.sh: pre-vendoring security scanner
  - Fixed angle-bracket includes in 18 grammars
  - Fixed PureScript scanner const mismatch
  - Fixed VHDL scanner void* API signatures
  - Fixed RST tree_sitter_rst/ subdirectory include paths
  - Copied crystal unicode.c (extra scanner dependency)

All new languages start with minimal lang specs (module_types only).
Function/class/call extraction specs to be refined incrementally.

Author: test

internal/cbm/cbm.h

@@ -75,6 +75,95 @@ typedef enum {
     CBM_LANG_FORM,
     CBM_LANG_MAGMA,
     CBM_LANG_WOLFRAM,
+    CBM_LANG_SOLIDITY,
+    CBM_LANG_TYPST,
+    CBM_LANG_GDSCRIPT,
+    CBM_LANG_GLEAM,
+    CBM_LANG_POWERSHELL,
+    CBM_LANG_PASCAL,
+    CBM_LANG_DLANG,
+    CBM_LANG_NIM,
+    CBM_LANG_SCHEME,
+    CBM_LANG_FENNEL,
+    CBM_LANG_FISH,
+    CBM_LANG_AWK,
+    CBM_LANG_ZSH,
+    CBM_LANG_TCL,
+    CBM_LANG_ADA,
+    CBM_LANG_AGDA,
+    CBM_LANG_RACKET,
+    CBM_LANG_ODIN,
+    CBM_LANG_RESCRIPT,
+    CBM_LANG_PURESCRIPT,
+    CBM_LANG_NICKEL,
+    CBM_LANG_CRYSTAL,
+    CBM_LANG_TEAL,
+    CBM_LANG_HARE,
+    CBM_LANG_PONY,
+    CBM_LANG_LUAU,
+    CBM_LANG_JANET,
+    CBM_LANG_SWAY,
+    CBM_LANG_NASM,
+    CBM_LANG_ASSEMBLY,
+    CBM_LANG_ASTRO,
+    CBM_LANG_BLADE,
+    CBM_LANG_JUST,
+    CBM_LANG_GOTEMPLATE,
+    CBM_LANG_TEMPL,
+    CBM_LANG_LIQUID,
+    CBM_LANG_JINJA2,
+    CBM_LANG_PRISMA,
+    CBM_LANG_HYPRLANG,
+    CBM_LANG_DOTENV,
+    CBM_LANG_DIFF,
+    CBM_LANG_WGSL,
+    CBM_LANG_KDL,
+    CBM_LANG_JSON5,
+    CBM_LANG_JSONNET,
+    CBM_LANG_RON,
+    CBM_LANG_THRIFT,
+    CBM_LANG_CAPNP,
+    CBM_LANG_PROPERTIES,
+    CBM_LANG_SSHCONFIG,
+    CBM_LANG_BIBTEX,
+    CBM_LANG_STARLARK,
+    CBM_LANG_BICEP,
+    CBM_LANG_CSV,
+    CBM_LANG_REQUIREMENTS,
+    CBM_LANG_HLSL,
+    CBM_LANG_VHDL,
+    CBM_LANG_SYSTEMVERILOG,
+    CBM_LANG_DEVICETREE,
+    CBM_LANG_LINKERSCRIPT,
+    CBM_LANG_GN,
+    CBM_LANG_KCONFIG,
+    CBM_LANG_BITBAKE,
+    CBM_LANG_SMALI,
+    CBM_LANG_TABLEGEN,
+    CBM_LANG_ISPC,
+    CBM_LANG_CAIRO,
+    CBM_LANG_MOVE,
+    CBM_LANG_SQUIRREL,
+    CBM_LANG_FUNC,
+    CBM_LANG_REGEX,
+    CBM_LANG_JSDOC,
+    CBM_LANG_RST,
+    CBM_LANG_BEANCOUNT,
+    CBM_LANG_MERMAID,
+    CBM_LANG_PUPPET,
+    CBM_LANG_PO,
+    CBM_LANG_GITATTRIBUTES,
+    CBM_LANG_GITIGNORE,
+    CBM_LANG_SLANG,
+    CBM_LANG_LLVM_IR,
+    CBM_LANG_SMITHY,
+    CBM_LANG_WIT,
+    CBM_LANG_TLAPLUS,
+    CBM_LANG_PKL,
+    CBM_LANG_GOMOD,
+    CBM_LANG_APEX,
+    CBM_LANG_SOQL,
+    CBM_LANG_SOSL,
     CBM_LANG_KUSTOMIZE, // kustomization.yaml — Kubernetes overlay tool
     CBM_LANG_K8S,       // Generic Kubernetes manifest (apiVersion: detected)
     CBM_LANG_COUNT

internal/cbm/grammar_ada.c

@@ -0,0 +1,3 @@
+// Vendored tree-sitter grammar: ada
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/ada/parser.c"

internal/cbm/grammar_agda.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: agda
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/agda/parser.c"
+#include "vendored/grammars/agda/scanner.c"

internal/cbm/grammar_apex.c

@@ -0,0 +1,3 @@
+// Vendored tree-sitter grammar: apex
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/apex/parser.c"

internal/cbm/grammar_assembly.c

@@ -0,0 +1,3 @@
+// Vendored tree-sitter grammar: assembly
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/assembly/parser.c"

internal/cbm/grammar_astro.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: astro
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/astro/parser.c"
+#include "vendored/grammars/astro/scanner.c"

internal/cbm/grammar_awk.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: awk
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/awk/parser.c"
+#include "vendored/grammars/awk/scanner.c"

internal/cbm/grammar_beancount.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: beancount
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/beancount/parser.c"
+#include "vendored/grammars/beancount/scanner.c"

internal/cbm/grammar_bibtex.c

@@ -0,0 +1,3 @@
+// Vendored tree-sitter grammar: bibtex
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/bibtex/parser.c"

internal/cbm/grammar_bicep.c

@@ -0,0 +1,4 @@
+// Vendored tree-sitter grammar: bicep
+// Each grammar compiled as separate unit (conflicting static symbols).
+#include "vendored/grammars/bicep/parser.c"
+#include "vendored/grammars/bicep/scanner.c"