feat(config): custom weight thresholds via CEL (#688)

* feat(config): add Thresholds to the top level config file

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore(config): make String() on ExpressionOrList join the component expressions

Signed-off-by: Xe Iaso <me@xeiaso.net>

* test(config): ensure unparseable json fails

Signed-off-by: Xe Iaso <me@xeiaso.net>

* fix(config): if no thresholds are set, use the default thresholds

Signed-off-by: Xe Iaso <me@xeiaso.net>

* feat(policy): half implement thresholds

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore(policy): continue wiring things up

Signed-off-by: Xe Iaso <me@xeiaso.net>

* feat(lib): wire up thresholds

Signed-off-by: Xe Iaso <me@xeiaso.net>

* test(lib): handle behavior from legacy configurations

Signed-off-by: Xe Iaso <me@xeiaso.net>

* docs: document thresholds

Signed-off-by: Xe Iaso <me@xeiaso.net>

* docs: update CHANGELOG, refer to threshold configuration

Signed-off-by: Xe Iaso <me@xeiaso.net>

* fix(lib): fix build

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore(lib): fix U1000

Signed-off-by: Xe Iaso <me@xeiaso.net>

---------

Signed-off-by: Xe Iaso <me@xeiaso.net>
Signed-off-by: Jason Cameron <git@jasoncameron.dev>
Co-authored-by: Jason Cameron <git@jasoncameron.dev>
This commit is contained in:
Xe Iaso 2025-06-18 16:58:31 -04:00 committed by GitHub
parent 1d5fa49eb0
commit 226cf36bf7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 683 additions and 305 deletions

View file

@ -9,20 +9,12 @@ import (
"github.com/google/cel-go/ext"
)
// NewEnvironment creates a new CEL environment, this is the set of
// BotEnvironment creates a new CEL environment, this is the set of
// variables and functions that are passed into the CEL scope so that
// Anubis can fail loudly and early when something is invalid instead
// of blowing up at runtime.
func NewEnvironment() (*cel.Env, error) {
return cel.NewEnv(
ext.Strings(
ext.StringsLocale("en_US"),
ext.StringsValidateFormatCalls(true),
),
// default all timestamps to UTC
cel.DefaultUTCTimeZone(true),
func BotEnvironment() (*cel.Env, error) {
return New(
// Variables exposed to CEL programs:
cel.Variable("remoteAddress", cel.StringType),
cel.Variable("host", cel.StringType),
@ -31,8 +23,27 @@ func NewEnvironment() (*cel.Env, error) {
cel.Variable("path", cel.StringType),
cel.Variable("query", cel.MapType(cel.StringType, cel.StringType)),
cel.Variable("headers", cel.MapType(cel.StringType, cel.StringType)),
)
}
// Functions exposed to CEL programs:
// NewThreshold creates a new CEL environment for threshold checking.
func ThresholdEnvironment() (*cel.Env, error) {
return New(
cel.Variable("weight", cel.IntType),
)
}
func New(opts ...cel.EnvOption) (*cel.Env, error) {
args := []cel.EnvOption{
ext.Strings(
ext.StringsLocale("en_US"),
ext.StringsValidateFormatCalls(true),
),
// default all timestamps to UTC
cel.DefaultUTCTimeZone(true),
// Functions exposed to all CEL programs:
cel.Function("randInt",
cel.Overload("randInt_int",
[]*cel.Type{cel.IntType},
@ -47,12 +58,25 @@ func NewEnvironment() (*cel.Env, error) {
}),
),
),
)
}
args = append(args, opts...)
return cel.NewEnv(args...)
}
// Compile takes CEL environment and syntax tree then emits an optimized
// Program for execution.
func Compile(env *cel.Env, ast *cel.Ast) (cel.Program, error) {
func Compile(env *cel.Env, src string) (cel.Program, error) {
intermediate, iss := env.Compile(src)
if iss != nil {
return nil, iss.Err()
}
ast, iss := env.Check(intermediate)
if iss != nil {
return nil, iss.Err()
}
return env.Program(
ast,
cel.EvalOptions(

View file

@ -1,104 +0,0 @@
package expressions
import (
"errors"
"fmt"
"strings"
"github.com/google/cel-go/cel"
)
// JoinOperator is a type wrapper for and/or operators.
//
// This is a separate type so that validation can be done at the type level.
type JoinOperator string
// Possible values for JoinOperator
const (
JoinAnd JoinOperator = "&&"
JoinOr JoinOperator = "||"
)
// Valid ensures that JoinOperator is semantically valid.
func (jo JoinOperator) Valid() error {
switch jo {
case JoinAnd, JoinOr:
return nil
default:
return ErrWrongJoinOperator
}
}
var (
ErrWrongJoinOperator = errors.New("expressions: invalid join operator")
ErrNoExpressions = errors.New("expressions: cannot join zero expressions")
ErrCantCompile = errors.New("expressions: can't compile one expression")
)
// JoinClauses joins a list of compiled clauses into one big if statement.
//
// Imagine the following two clauses:
//
// ball.color == "red"
// ball.shape == "round"
//
// JoinClauses would emit one "joined" clause such as:
//
// ( ball.color == "red" ) && ( ball.shape == "round" )
func JoinClauses(env *cel.Env, operator JoinOperator, clauses ...*cel.Ast) (*cel.Ast, error) {
if err := operator.Valid(); err != nil {
return nil, fmt.Errorf("%w: wanted && or ||, got: %q", err, operator)
}
switch len(clauses) {
case 0:
return nil, ErrNoExpressions
case 1:
return clauses[0], nil
}
var exprs []string
var errs []error
for _, clause := range clauses {
clauseStr, err := cel.AstToString(clause)
if err != nil {
errs = append(errs, err)
continue
}
exprs = append(exprs, "( "+clauseStr+" )")
}
if len(errs) != 0 {
return nil, fmt.Errorf("errors while decompiling statements: %w", errors.Join(errs...))
}
statement := strings.Join(exprs, " "+string(operator)+" ")
result, iss := env.Compile(statement)
if iss != nil {
return nil, iss.Err()
}
return result, nil
}
func Join(env *cel.Env, operator JoinOperator, clauses ...string) (*cel.Ast, error) {
var statements []*cel.Ast
var errs []error
for _, clause := range clauses {
stmt, iss := env.Compile(clause)
if iss != nil && iss.Err() != nil {
errs = append(errs, fmt.Errorf("%w: %q gave: %w", ErrCantCompile, clause, iss.Err()))
continue
}
statements = append(statements, stmt)
}
if len(errs) != 0 {
return nil, fmt.Errorf("errors while joining clauses: %w", errors.Join(errs...))
}
return JoinClauses(env, operator, statements...)
}

View file

@ -1,90 +0,0 @@
package expressions
import (
"errors"
"testing"
"github.com/google/cel-go/cel"
)
func TestJoin(t *testing.T) {
env, err := NewEnvironment()
if err != nil {
t.Fatal(err)
}
for _, tt := range []struct {
err error
name string
op JoinOperator
resultStr string
clauses []string
}{
{
name: "no-clauses",
clauses: []string{},
op: JoinAnd,
err: ErrNoExpressions,
},
{
name: "one-clause-identity",
clauses: []string{`remoteAddress == "8.8.8.8"`},
op: JoinAnd,
err: nil,
resultStr: `remoteAddress == "8.8.8.8"`,
},
{
name: "multi-clause-and",
clauses: []string{
`remoteAddress == "8.8.8.8"`,
`host == "anubis.techaro.lol"`,
},
op: JoinAnd,
err: nil,
resultStr: `remoteAddress == "8.8.8.8" && host == "anubis.techaro.lol"`,
},
{
name: "multi-clause-or",
clauses: []string{
`remoteAddress == "8.8.8.8"`,
`host == "anubis.techaro.lol"`,
},
op: JoinOr,
err: nil,
resultStr: `remoteAddress == "8.8.8.8" || host == "anubis.techaro.lol"`,
},
{
name: "git-user-agent",
clauses: []string{
`userAgent.startsWith("git/") || userAgent.contains("libgit")`,
`"Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"`,
},
op: JoinAnd,
err: nil,
resultStr: `(userAgent.startsWith("git/") || userAgent.contains("libgit")) && "Git-Protocol" in headers &&
headers["Git-Protocol"] == "version=2"`,
},
} {
t.Run(tt.name, func(t *testing.T) {
result, err := Join(env, tt.op, tt.clauses...)
if !errors.Is(err, tt.err) {
t.Errorf("wanted error %v but got: %v", tt.err, err)
}
if tt.err != nil {
return
}
program, err := cel.AstToString(result)
if err != nil {
t.Fatalf("can't decompile program: %v", err)
}
if tt.resultStr != program {
t.Logf("wanted: %s", tt.resultStr)
t.Logf("got: %s", program)
t.Error("program did not compile as expected")
}
})
}
}