tjcravey/sojuboy
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: expand .env example to show max/large values; add SUMM_TIMEOUT and summarizer tunables\n\nfeat: summarizer improvements\n- readability extraction for articles\n- image links passed to model as vision inputs\n- configurable max groups/links/bytes and timeout\n- higher default ceilings; resilient fallback summary

Browse source
This commit is contained in:
Thomas Cravey 2025-08-15 20:41:31 -05:00
parent 2954e85e7a
commit 9ecf4f4f4c
7 changed files with 296 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

24
internal/config/config.go
View file

@ -28,16 +28,18 @@ type Config struct {
PushoverAPIToken string
// Summarizer / LLM
LLMProvider string
OpenAIAPIKey string
OpenAIBaseURL string
OpenAIModel string
OpenAIMaxTokens int
SummFollowLinks bool
SummLinkTimeout time.Duration
SummLinkMaxBytes int
SummGroupWindow time.Duration
SummMaxLinks int
LLMProvider string
OpenAIAPIKey string
OpenAIBaseURL string
OpenAIModel string
OpenAIMaxTokens int
SummFollowLinks bool
SummLinkTimeout time.Duration
SummLinkMaxBytes int
SummGroupWindow time.Duration
SummMaxLinks int
SummMaxGroups int
SummarizerTimeout time.Duration
// Digests
DigestCron string
@ -90,6 +92,8 @@ func FromEnv() Config {
cfg.SummLinkMaxBytes = getEnvInt("SUMM_LINK_MAX_BYTES", 262144)
cfg.SummGroupWindow = getEnvDuration("SUMM_GROUP_WINDOW", 90*time.Second)
cfg.SummMaxLinks = getEnvInt("SUMM_MAX_LINKS", 5)
cfg.SummMaxGroups = getEnvInt("SUMM_MAX_GROUPS", 0)
cfg.SummarizerTimeout = getEnvDuration("SUMM_TIMEOUT", 5*time.Minute)
cfg.DigestCron = getEnv("DIGEST_CRON", "0 */6 * * *")
cfg.DigestWindow = getEnvDuration("DIGEST_WINDOW", 6*time.Hour)

10
internal/httpapi/server.go
View file

@ -32,6 +32,8 @@ type Server struct {
Logger *slog.Logger
Metrics *Metrics
Ready func() bool
// Optional timeout override for summarizer
SummarizerTimeout time.Duration
}
func (s *Server) Start(ctx context.Context) error {
@ -106,8 +108,12 @@ func (s *Server) handleTrigger(w http.ResponseWriter, r *http.Request) {
_, _ = w.Write([]byte("summarizer not configured"))
return
}
// Timeout summarization to avoid hung requests.
ctxSum, cancel := context.WithTimeout(ctx, 60*time.Second)
// Timeout summarization using configurable timeout (default 5m)
tout := s.SummarizerTimeout
if tout <= 0 {
tout = 5 * time.Minute
}
ctxSum, cancel := context.WithTimeout(ctx, tout)
defer cancel()
summary, err := s.Summarizer.Summarize(ctxSum, channel, msgs, window)
if err != nil {

150
internal/summarizer/openai.go
View file

@ -4,10 +4,14 @@ import (
"context"
"io"
"net/http"
"net/url"
"regexp"
"sort"
"strconv"
"strings"
"time"
readability "github.com/go-shiori/go-readability"
openai "github.com/sashabaranov/go-openai"
"sojuboy/internal/config"
@ -25,6 +29,7 @@ type OpenAI struct {
linkMaxBytes int
groupWindow time.Duration
maxLinks int
maxGroups int
}
func NewOpenAI(apiKey, baseURL, model string, maxTokens int) *OpenAI {
@ -40,6 +45,7 @@ func (o *OpenAI) ApplyConfig(cfg config.Config) {
o.linkMaxBytes = cfg.SummLinkMaxBytes
o.groupWindow = cfg.SummGroupWindow
o.maxLinks = cfg.SummMaxLinks
o.maxGroups = cfg.SummMaxGroups
}
func (o *OpenAI) Summarize(ctx context.Context, channel string, msgs []store.Message, window time.Duration) (string, error) {
@ -54,11 +60,25 @@ func (o *OpenAI) Summarize(ctx context.Context, channel string, msgs []store.Mes
// 1) Group multiline posts from same author within groupWindow
grouped := groupMessages(msgs, o.groupWindow)
// Apply group cap if configured (>0). 0 means no cap.
if o.maxGroups > 0 && len(grouped) > o.maxGroups {
grouped = grouped[len(grouped)-o.maxGroups:]
}
// 2) Extract links and optionally fetch a small amount of content
// 2) Extract links and optionally fetch content
links := extractLinks(grouped)
if o.followLinks && len(links) > 0 {
links = fetchLinkSnippets(ctx, links, o.linkTimeout, o.linkMaxBytes, o.maxLinks)
// Split image vs non-image
var imageURLs []string
var nonImageLinks []linkSnippet
for _, l := range links {
if isImageURL(l.url) {
imageURLs = append(imageURLs, l.url)
} else {
nonImageLinks = append(nonImageLinks, l)
}
}
if o.followLinks && len(nonImageLinks) > 0 {
nonImageLinks = fetchLinkSnippets(ctx, nonImageLinks, o.linkTimeout, o.linkMaxBytes, o.maxLinks)
}
// 3) Build a concise, natural prompt
@ -76,9 +96,9 @@ func (o *OpenAI) Summarize(ctx context.Context, channel string, msgs []store.Mes
b.WriteString(g.text)
b.WriteString("\n")
}
if len(links) > 0 {
if len(nonImageLinks) > 0 {
b.WriteString("\nReferenced content (snippets):\n")
for _, ln := range links {
for _, ln := range nonImageLinks {
b.WriteString("- ")
b.WriteString(ln.url)
b.WriteString(" → ")
@ -101,11 +121,25 @@ func (o *OpenAI) Summarize(ctx context.Context, channel string, msgs []store.Mes
}
reasoningLike := strings.HasPrefix(model, "gpt-5") || strings.HasPrefix(model, "o1") || strings.Contains(model, "reasoning")
// Build multimodal user message parts
userParts := []openai.ChatMessagePart{{Type: openai.ChatMessagePartTypeText, Text: prompt}}
// Limit images to o.maxLinks to avoid overloading
maxImgs := o.maxLinks
if len(imageURLs) > maxImgs {
imageURLs = imageURLs[:maxImgs]
}
for _, u := range imageURLs {
userParts = append(userParts, openai.ChatMessagePart{
Type: openai.ChatMessagePartTypeImageURL,
ImageURL: &openai.ChatMessageImageURL{URL: u},
})
}
req := openai.ChatCompletionRequest{
Model: model,
Messages: []openai.ChatCompletionMessage{
{Role: openai.ChatMessageRoleSystem, Content: sys},
{Role: openai.ChatMessageRoleUser, Content: prompt},
{Role: openai.ChatMessageRoleUser, MultiContent: userParts},
},
MaxCompletionTokens: o.maxTokens,
}
@ -118,9 +152,31 @@ func (o *OpenAI) Summarize(ctx context.Context, channel string, msgs []store.Mes
return "", err
}
if len(resp.Choices) == 0 {
return "", nil
return localFallbackSummary(grouped, append(nonImageLinks, linksFromImages(imageURLs)...)), nil
}
return strings.TrimSpace(resp.Choices[0].Message.Content), nil
out := strings.TrimSpace(resp.Choices[0].Message.Content)
if out == "" {
return localFallbackSummary(grouped, append(nonImageLinks, linksFromImages(imageURLs)...)), nil
}
return out, nil
}
func linksFromImages(imgs []string) []linkSnippet {
out := make([]linkSnippet, 0, len(imgs))
for _, u := range imgs {
out = append(out, linkSnippet{url: u})
}
return out
}
func isImageURL(u string) bool {
lu := strings.ToLower(u)
for _, ext := range []string{".jpg", ".jpeg", ".png", ".gif", ".webp"} {
if strings.HasSuffix(lu, ext) {
return true
}
}
return false
}
type linkSnippet struct {
@ -162,7 +218,16 @@ func extractLinks(msgs []groupedMsg) []linkSnippet {
links = append(links, linkSnippet{url: m})
}
}
return links
// de-dup
saw := make(map[string]bool)
dedup := make([]linkSnippet, 0, len(links))
for _, l := range links {
if !saw[l.url] {
saw[l.url] = true
dedup = append(dedup, l)
}
}
return dedup
}
func fetchLinkSnippets(ctx context.Context, links []linkSnippet, timeout time.Duration, maxBytes int, maxLinks int) []linkSnippet {
@ -190,15 +255,76 @@ func fetchLinkSnippets(ctx context.Context, links []linkSnippet, timeout time.Du
if err != nil || len(b) == 0 {
return
}
// naive text cleanup
text := string(b)
// Try readability for cleaner article text
if baseURL, perr := url.Parse(ln.url); perr == nil {
if art, err := readability.FromReader(strings.NewReader(text), baseURL); err == nil {
if at := strings.TrimSpace(art.TextContent); at != "" {
text = at
}
}
}
text = strings.ReplaceAll(text, "\r", "")
text = strings.TrimSpace(text)
if len(text) > 800 {
text = text[:800]
if len(text) > 2000 {
text = text[:2000]
}
out = append(out, linkSnippet{url: ln.url, snippet: text})
}()
}
return out
}
func localFallbackSummary(grouped []groupedMsg, links []linkSnippet) string {
if len(grouped) == 0 {
return ""
}
// simple counts
authors := map[string]int{}
for _, g := range grouped {
authors[g.author]++
}
authorList := make([]string, 0, len(authors))
for a := range authors {
authorList = append(authorList, a)
}
sort.Strings(authorList)
var b strings.Builder
b.WriteString("Summary (fallback)\n")
b.WriteString("- Messages: ")
b.WriteString(strconvI(len(grouped)))
b.WriteString(" groups by ")
b.WriteString(strconvI(len(authors)))
b.WriteString(" authors\n")
if len(links) > 0 {
b.WriteString("- Links: ")
for i, l := range links {
if i > 0 {
b.WriteString(", ")
}
b.WriteString(l.url)
}
b.WriteString("\n")
}
// include last few grouped lines as a teaser
tail := grouped
if len(tail) > 5 {
tail = tail[len(tail)-5:]
}
for _, g := range tail {
b.WriteString("• ")
b.WriteString(g.author)
b.WriteString(": ")
line := g.text
if len(line) > 200 {
line = line[:200] + "…"
}
b.WriteString(line)
b.WriteString("\n")
}
return strings.TrimSpace(b.String())
}
func strconvI(n int) string {
return strconv.Itoa(n)
}