servewaf: each decision heuristic is its own module (closes #195)

Each check servewaf runs on a request is a type in its own file behind
one interface, heuristic, and is registered in one of four ordered lists
in heuristics.go. Order and behaviour are unchanged.

Every refusal now logs heuristic, the name of the heuristic that made
it, and heuristic_figures, the figures it acted on. A ban by
refusal_limit or byte_limits after the answer logs after_answer_heuristic
and after_answer_heuristic_figures instead, so a line can name both. All
four are in docs/request-log.md, and SPEC.md names each heuristic at its
step.

Model: opus-5-5

SPEC.md

@@ -125,7 +125,7 @@ produces a final answer ends the checks. Step 15 runs for each request
 limits apply to the whole exchange. Each step names the section that holds its
 rules. Each check is a heuristic. Its name, in parentheses below, is the value
 of the request log's `heuristic` field. `refusal_limit` and `byte_limits` give
-theirs in `report_heuristic` instead.
+theirs in `after_answer_heuristic` instead.
 
 1. `GET /_smallwebwaf/healthz` is answered at once by `rproxy`, before any
    check, so a health checker never needs an exemption and is never refused.

docs/request-log.md

@@ -127,10 +127,11 @@ Every one of these lines has:
     - `core_rule_set`: `score`, and `threshold`, `SWWAF_WAF_ANOMALY_THRESHOLD`;
     - `refusal_limit`: `window`, `count` and `limit`, of the error burst;
     - `byte_limits`: `window`, `count` and `limit`, the count in bytes.
-- `report_heuristic`: the heuristic that banned the client after `servewaf`
+- `after_answer_heuristic`: the heuristic that banned the client after
-  answered the request, in `observe` mode too: `refusal_limit` or `byte_limits`.
+  `servewaf` answered the request, in `observe` mode too: `refusal_limit` or
-- `report_heuristic_figures`: an object of the figures that heuristic acted on,
+  `byte_limits`.
-  as listed above.
+- `after_answer_heuristic_figures`: an object of the figures that heuristic
+  acted on, as listed above.
 
     `byte_limits` bans when the report comes, so only the `report` line names
     it.

internal/requestlog/requestlog.go

@@ -136,10 +136,11 @@ type Line struct {
 	// name.
 	Heuristic        string         `json:"heuristic,omitempty"`
 	HeuristicFigures map[string]any `json:"heuristic_figures,omitempty"`
-	// ReportHeuristic and ReportHeuristicFigures are the same for the
+	// AfterAnswerHeuristic and AfterAnswerHeuristicFigures are the same for
-	// heuristic that banned the client after servewaf answered the request.
+	// the heuristic that banned the client after servewaf answered the
-	ReportHeuristic        string         `json:"report_heuristic,omitempty"`
+	// request.
-	ReportHeuristicFigures map[string]any `json:"report_heuristic_figures,omitempty"`
+	AfterAnswerHeuristic        string         `json:"after_answer_heuristic,omitempty"`
+	AfterAnswerHeuristicFigures map[string]any `json:"after_answer_heuristic_figures,omitempty"` //nolint:lll // a struct tag cannot be split
 	// LimitPercent and LimitPercentSetting are, for a request the rate
 	// limits counted whose client a biased threshold gives a percentage of
 	// the rate limits below 100, that percentage and the setting that gave

internal/servewaf/bytelimits_test.go

@@ -104,12 +104,12 @@ func TestByteLimitBanNamesItsHeuristicWindowCountAndLimit(t *testing.T) {
 	s, _ := startWithAnswers(t, map[string]string{bytesLimitPerMinute: byteLimit})
 
 	line, _ := s.download()
-	wantReportHeuristic(t, line, "", "null")
+	wantAfterAnswerHeuristic(t, line, "", "null")
 
 	// Two answers of 70 bytes are over the limit of 99.
 	line, _ = s.download()
 	wantHeuristic(t, line, "", "null")
-	wantReportHeuristic(t, line, "byte_limits",
+	wantAfterAnswerHeuristic(t, line, "byte_limits",
 		`{"window": "minute", "count": 140, "limit": 99}`)
 }
 

internal/servewaf/headerlimits.go

@@ -25,7 +25,7 @@ func (headerLimits) name() string { return "header_limits" }
 
 func (headerLimits) check(_ context.Context, rq *request, _ time.Time) *verdict {
 	fields, cookies := rq.headerCounts()
-	if fields <= maxHeaderFields && cookies <= maxCookies {
+	if !overHeaderLimits(fields, cookies) {
 		return nil
 	}
 
@@ -38,12 +38,10 @@ func (headerLimits) check(_ context.Context, rq *request, _ time.Time) *verdict
 	}
 }
 
-// overHeaderLimits reports whether the request is over the header limits: it
+// overHeaderLimits reports whether a request with these counts of header fields
-// has more than maxHeaderFields fields or more than maxCookies cookies, as
+// and cookies, as headerCounts counts them, is over the header limits: it has
-// headerCounts counts them.
+// more than maxHeaderFields fields or more than maxCookies cookies.
-func (rq *request) overHeaderLimits() bool {
+func overHeaderLimits(fields, cookies int) bool {
-	fields, cookies := rq.headerCounts()
-
 	return fields > maxHeaderFields || cookies > maxCookies
 }
 

internal/servewaf/heuristics.go

@@ -104,15 +104,15 @@ func (rq *request) runHeuristics(
 }
 
 // runBanningHeuristics runs list, afterAnswer or onReport, on the request at
-// the time it is called. The log line's report_heuristic and
+// the time it is called. The log line's after_answer_heuristic and
-// report_heuristic_figures name the heuristic that gave a verdict, and give its
+// after_answer_heuristic_figures name the heuristic that gave a verdict, and
-// figures, so that heuristic and heuristic_figures still name the one that
+// give its figures, so that heuristic and heuristic_figures still name the one
-// refused the request. ctx is the request's own context.
+// that refused the request. ctx is the request's own context.
 func (rq *request) runBanningHeuristics(ctx context.Context, list []heuristic) {
 	name, v := rq.firstVerdict(ctx, list, rq.h.now())
 	if v != nil {
-		rq.line.ReportHeuristic = name
+		rq.line.AfterAnswerHeuristic = name
-		rq.line.ReportHeuristicFigures = v.figures
+		rq.line.AfterAnswerHeuristicFigures = v.figures
 	}
 }
 

internal/servewaf/refusallimit_test.go

@@ -115,13 +115,13 @@ func TestRefusalLimitBanNamesItsHeuristicWindowCountAndLimit(t *testing.T) {
 
 	line := blockRule.send(s, client)
 	wantHeuristic(t, line, "rule_files", ruleFigures)
-	wantReportHeuristic(t, line, "", "null")
+	wantAfterAnswerHeuristic(t, line, "", "null")
 
 	// The second refusal is the request refusal_limit bans for, and the line
 	// names both.
 	line = blockRule.send(s, client)
 	wantHeuristic(t, line, "rule_files", ruleFigures)
-	wantReportHeuristic(t, line, "refusal_limit",
+	wantAfterAnswerHeuristic(t, line, "refusal_limit",
 		`{"window": "minute", "count": 2, "limit": 1}`)
 }
 

internal/servewaf/requestlog_test.go

@@ -286,16 +286,17 @@ func wantHeuristic(t *testing.T, line logLine, heuristic, figures string) {
 	}
 }
 
-// wantReportHeuristic checks report_heuristic and report_heuristic_figures as
+// wantAfterAnswerHeuristic checks after_answer_heuristic and
-// wantHeuristic checks heuristic and heuristic_figures.
+// after_answer_heuristic_figures as wantHeuristic checks heuristic and
-func wantReportHeuristic(t *testing.T, line logLine, heuristic, figures string) {
+// heuristic_figures.
+func wantAfterAnswerHeuristic(t *testing.T, line logLine, heuristic, figures string) {
 	t.Helper()
 
-	if line.ReportHeuristic != heuristic ||
+	if line.AfterAnswerHeuristic != heuristic ||
-		!reflect.DeepEqual(line.ReportHeuristicFigures, decodeFigures(t, figures)) {
+		!reflect.DeepEqual(line.AfterAnswerHeuristicFigures, decodeFigures(t, figures)) {
-		t.Errorf("log line has report_heuristic %q with report_heuristic_figures %v, "+
+		t.Errorf("log line has after_answer_heuristic %q with "+
-			"want %q with %s",
+			"after_answer_heuristic_figures %v, want %q with %s",
-			line.ReportHeuristic, line.ReportHeuristicFigures, heuristic, figures)
+			line.AfterAnswerHeuristic, line.AfterAnswerHeuristicFigures, heuristic, figures)
 	}
 }
 

internal/servewaf/servewaf.go

@@ -152,7 +152,7 @@ func (rq *request) refusedWhateverTheAnswer(now time.Time) bool {
 
 	_, decided := rq.crowdSecDecisionInForce(now)
 
-	return decided || rq.overHeaderLimits() ||
+	return decided || overHeaderLimits(rq.headerCounts()) ||
 		rq.refusedByBlocklists(rq.h.lists.ListedBy(rq.client)) ||
 		rq.overAWholeRateLimit(now)
 }