Merge pull request #22 from buildkite/catkins/process-job-logs

Author: catkins

go.mod

@@ -5,6 +5,8 @@ go 1.24.2
 require (
 	github.com/alecthomas/kong v1.10.0
 	github.com/buildkite/go-buildkite/v4 v4.1.0
+	github.com/buildkite/terminal-to-html/v3 v3.16.8
+	github.com/huantt/plaintext-extractor v1.1.0
 	github.com/mark3labs/mcp-go v0.20.1
 	github.com/rs/zerolog v1.34.0
 	github.com/stretchr/testify v1.9.0
@@ -19,7 +21,7 @@ require (
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/yosida95/uritemplate/v3 v3.0.2 // indirect
-	golang.org/x/net v0.38.0 // indirect
+	golang.org/x/net v0.39.0 // indirect
 	golang.org/x/sys v0.32.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -6,20 +6,24 @@ github.com/alecthomas/repr v0.4.0 h1:GhI2A8MACjfegCPVq9f1FLvIBS+DrQ2KQBFZP1iFzXc
 github.com/alecthomas/repr v0.4.0/go.mod h1:Fr0507jx4eOXV7AlPV6AVZLYrLIuIeSOWtW57eE/O/4=
 github.com/buildkite/go-buildkite/v4 v4.1.0 h1:n1f3EAe8/64ju9QjSWJYMjD8++mn1pOLK/tZscD5DKo=
 github.com/buildkite/go-buildkite/v4 v4.1.0/go.mod h1:xlYVIETMCk46KUkmfRoztoIf888KwdY5uZXNinZ1PX0=
+github.com/buildkite/terminal-to-html/v3 v3.16.8 h1:QN/daUob6cmK8GcdKnwn9+YTlPr1vNj+oeAIiJK6fPc=
+github.com/buildkite/terminal-to-html/v3 v3.16.8/go.mod h1:+k1KVKROZocrTLsEQ9PEf9A+8+X8uaVV5iO1ZIOwKYM=
 github.com/cenkalti/backoff v1.1.1-0.20171020064038-309aa717adbf h1:yxlp0s+Sge9UsKEK0Bsvjiopb9XRk+vxylmZ9eGBfm8=
 github.com/cenkalti/backoff v1.1.1-0.20171020064038-309aa717adbf/go.mod h1:90ReRw6GdpyfrHakVjL/QHaoyV4aDUVVkXQJJJ3NXXM=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
-github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
-github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/go-querystring v1.0.0 h1:Xkwi/a1rcvNg1PPYe5vI8GbeBY/jrVuDX5ASuANWTrk=
 github.com/google/go-querystring v1.0.0/go.mod h1:odCYkC5MyYFN7vkCjXpyrEuKhc/BUO6wN/zVPAxq5ck=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
 github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
+github.com/huantt/plaintext-extractor v1.1.0 h1:dZkJN0fGZf1o8x9UdR6hHqkZnqIwX94YlGJ/lSXUZ5c=
+github.com/huantt/plaintext-extractor v1.1.0/go.mod h1:zIIbG/hZnsnLgzDbZ2T8fOrA4SLGWCoHWWYZo0Anx9c=
 github.com/mark3labs/mcp-go v0.20.1 h1:E1Bbx9K8d8kQmDZ1QHblM38c7UU2evQ2LlkANk1U/zw=
 github.com/mark3labs/mcp-go v0.20.1/go.mod h1:KmJndYv7GIgcPVwEKJjNcbhVQ+hJGJhrCCB/9xITzpE=
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
@@ -39,8 +43,8 @@ github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsT
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
-golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
-golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/net v0.39.0 h1:ZCu7HMWDxpXpaiKdhzIfaltL9Lp31x/3fCP11bc6/fY=
+golang.org/x/net v0.39.0/go.mod h1:X7NRbYVEA+ewNkCNyJ513WmMdQ3BineSwVtN2zD/d+E=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

internal/buildkite/job_logs.go

@@ -2,11 +2,11 @@ package buildkite
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
 
+	"github.com/buildkite/buildkite-mcp-server/internal/buildkite/joblogs"
 	"github.com/buildkite/go-buildkite/v4"
 	"github.com/mark3labs/mcp-go/mcp"
 	"github.com/mark3labs/mcp-go/server"
@@ -66,11 +66,13 @@ func GetJobLogs(ctx context.Context, client *buildkite.Client) (tool mcp.Tool, h
 				return mcp.NewToolResultError(fmt.Sprintf("failed to get issue: %s", string(body))), nil
 			}
 
-			r, err := json.Marshal(joblog)
+			// the default logs that come from the API can be pretty dense with ANSI codes or HTML
+			// so we can strip that out before returning it to the LLM
+			processedLog, err := joblogs.Process(joblog)
 			if err != nil {
-				return nil, fmt.Errorf("failed to marshal job logs: %w", err)
+				return nil, fmt.Errorf("failed to process job log: %w", err)
 			}
 
-			return mcp.NewToolResultText(string(r)), nil
+			return mcp.NewToolResultText(processedLog), nil
 		}
 }

internal/buildkite/joblogs/process.go

@@ -0,0 +1,49 @@
+package joblogs
+
+import (
+	"fmt"
+	"regexp"
+	"strings"
+
+	"github.com/buildkite/go-buildkite/v4"
+	"github.com/buildkite/terminal-to-html/v3"
+	"github.com/huantt/plaintext-extractor"
+)
+
+var timeTagRegexp = regexp.MustCompile(`<time[^>]*>.*?</time>`)
+
+// Process accepts job logs from the Buildkite API and strips out formatting
+// to reduce the number of tokens sent to the LLM
+func Process(jobLog buildkite.JobLog) (string, error) {
+	screen, err := terminal.NewScreen()
+	if err != nil {
+		return "", fmt.Errorf("failed to create terminal screen: %w", err)
+	}
+
+	if _, err = screen.Write([]byte(jobLog.Content)); err != nil {
+		return "", fmt.Errorf("failed to write to terminal screen: %w", err)
+	}
+
+	html := screen.AsHTML()
+	output := strings.Builder{}
+	extractor := plaintext.NewHtmlExtractor()
+
+	for line := range strings.Lines(html) {
+		// remove timestamps to save a few more tokens
+		line = timeTagRegexp.ReplaceAllString(line, "")
+
+		plainText, err := extractor.PlainText(line)
+		if err != nil {
+			return "", fmt.Errorf("failed to extract plain text: %w", err)
+		}
+
+		if plainText == nil {
+			empty := ""
+			plainText = &empty
+		}
+
+		output.WriteString(*plainText + "\n")
+	}
+
+	return output.String(), nil
+}

internal/buildkite/joblogs/process_test.go

@@ -0,0 +1,41 @@
+package joblogs
+
+import (
+	"os"
+	"testing"
+
+	"github.com/buildkite/go-buildkite/v4"
+)
+
+func TestProcess(t *testing.T) {
+	rawLog, err := os.ReadFile("testdata/bash-example.log")
+	if err != nil {
+		t.Fatalf("failed to read test log file: %v", err)
+	}
+
+	jobLog := buildkite.JobLog{Content: string(rawLog)}
+
+	// Process the job log
+	processedLog, err := Process(jobLog)
+	if err != nil {
+		t.Fatalf("expected no error, got %v", err)
+	}
+
+	// write out golden file if WRITE_JOB_LOG_GOLDEN_FILE is set
+	if os.Getenv("WRITE_JOB_LOG_GOLDEN_FILE") != "" {
+		err = os.WriteFile("testdata/processed.log", []byte(processedLog), 0644)
+		if err != nil {
+			t.Fatalf("failed to write processed log golden file: %v", err)
+		}
+	}
+
+	expectedLog, err := os.ReadFile("testdata/processed.log")
+	if err != nil {
+		t.Fatalf("failed to read processed log golden file: %v", err)
+	}
+
+	// Check if the processed log is as expected
+	if processedLog != string(expectedLog) {
+		t.Fatalf("expected %q, got %q", expectedLog, processedLog)
+	}
+}