fix: lint issues — gci formatting and testifylint float comparisons

Assisted-By: docker-agent

Author: hamza-jeddad

pkg/evaluation/eval_test.go

@@ -658,7 +658,7 @@ func TestProgressBarPrintResult(t *testing.T) {
 				Size:              "S",
 				RelevanceExpected: 2,
 				RelevancePassed:   1,
-				RelevanceResults:   []RelevanceResult{{Criterion: "check failed", Passed: false, Reason: "did not meet criteria"}},
+				RelevanceResults:  []RelevanceResult{{Criterion: "check failed", Passed: false, Reason: "did not meet criteria"}},
 			},
 			wantContains: []string{
 				"✗ mixed-session", // overall failed

pkg/evaluation/save_test.go

@@ -256,8 +256,8 @@ func TestSaveRunSessionsJSON(t *testing.T) {
 	// Verify structured relevance check
 	require.NotNil(t, sess1Loaded.EvalResult.Checks.Relevance)
 	assert.True(t, sess1Loaded.EvalResult.Checks.Relevance.Passed)
-	assert.Equal(t, float64(2), sess1Loaded.EvalResult.Checks.Relevance.PassedCount)
-	assert.Equal(t, float64(2), sess1Loaded.EvalResult.Checks.Relevance.Total)
+	assert.InDelta(t, 2, sess1Loaded.EvalResult.Checks.Relevance.PassedCount, 0.01)
+	assert.InDelta(t, 2, sess1Loaded.EvalResult.Checks.Relevance.Total, 0.01)
 
 	// No size or tool calls checks were configured
 	assert.Nil(t, sess1Loaded.EvalResult.Checks.Size)
@@ -276,7 +276,7 @@ func TestSaveRunSessionsJSON(t *testing.T) {
 	// Verify structured relevance check with per-criterion results
 	require.NotNil(t, sess2Loaded.EvalResult.Checks.Relevance)
 	assert.False(t, sess2Loaded.EvalResult.Checks.Relevance.Passed)
-	assert.Equal(t, float64(1), sess2Loaded.EvalResult.Checks.Relevance.PassedCount)
+	assert.InDelta(t, 1, sess2Loaded.EvalResult.Checks.Relevance.PassedCount, 0.01)
 	assert.Equal(t, float64(2), sess2Loaded.EvalResult.Checks.Relevance.Total)
 	require.Len(t, sess2Loaded.EvalResult.Checks.Relevance.Results, 2)
 

pkg/evaluation/types.go

@@ -26,9 +26,9 @@ type Result struct {
 	SizeExpected      string            `json:"size_expected"`
 	ToolCallsScore    float64           `json:"tool_calls_score"`
 	ToolCallsExpected float64           `json:"tool_calls_score_expected"`
-	RelevancePassed    float64           `json:"relevance"`
-	RelevanceExpected   float64           `json:"relevance_expected"`
-	RelevanceResults    []RelevanceResult `json:"relevance_results,omitempty"`
+	RelevancePassed   float64           `json:"relevance"`
+	RelevanceExpected float64           `json:"relevance_expected"`
+	RelevanceResults  []RelevanceResult `json:"relevance_results,omitempty"`
 	Error             string            `json:"error,omitempty"`
 	RawOutput         []map[string]any  `json:"raw_output,omitempty"`
 	Session           *session.Session  `json:"-"` // Full session for database storage (not in JSON)

pkg/session/session.go

@@ -234,13 +234,13 @@ func NewSubSessionItem(subSession *Session) Item {
 
 // EvalResult contains the evaluation scoring outcome for a session.
 type EvalResult struct {
-	Passed       bool              `json:"passed"`
-	Successes    []string          `json:"successes,omitempty"`
-	Failures     []string          `json:"failures,omitempty"`
-	Error        string            `json:"error,omitempty"`
-	Cost         float64           `json:"cost"`
-	OutputTokens int64             `json:"output_tokens"`
-	Checks       EvalResultChecks  `json:"checks"`
+	Passed       bool             `json:"passed"`
+	Successes    []string         `json:"successes,omitempty"`
+	Failures     []string         `json:"failures,omitempty"`
+	Error        string           `json:"error,omitempty"`
+	Cost         float64          `json:"cost"`
+	OutputTokens int64            `json:"output_tokens"`
+	Checks       EvalResultChecks `json:"checks"`
 }
 
 // EvalResultChecks groups the individual check results.
@@ -266,9 +266,9 @@ type ToolCallsCheck struct {
 
 // RelevanceCheck contains the result of the LLM judge relevance check.
 type RelevanceCheck struct {
-	Passed      bool                      `json:"passed"`
-	PassedCount float64                   `json:"passed_count"`
-	Total       float64                   `json:"total"`
+	Passed      bool                       `json:"passed"`
+	PassedCount float64                    `json:"passed_count"`
+	Total       float64                    `json:"total"`
 	Results     []RelevanceCriterionResult `json:"results"`
 }