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

README.md

@@ -31,14 +31,14 @@ Runtime modules:
 - `internal/notifier`: Pushover notifier (pluggable interface)
 - `internal/summarizer`: OpenAI client with GPT-5 defaults, GPT-4o-mini fallback
 - `internal/scheduler`: cron-based digest scheduling and daily retention job
-- `internal/httpapi`: `/healthz`, `/tail`, `/trigger`, `/metrics`
+- `internal/httpapi`: `/healthz`, `/ready`, `/tail`, `/trigger`, `/metrics`
 - `internal/config`: env config loader and helpers
 
 ## Features
 
 - Mention/keyword detection: punctuation-tolerant (letters, digits, `_` and `-` are word chars)
 - Mention tuning: allow/deny channels, urgent keywords bypass quiet hours, rate limiting
-- AI digest generation: concise natural summaries (no rigid sections); integrates pasted multi-line posts and referenced link context
+- AI digest generation: concise natural summaries (no rigid sections); integrates pasted multi-line posts and referenced link context; image links sent to GPT‑5 as vision inputs
 - Configurable schedules (cron), quiet hours, and summary parameters
 - Local persistence with retention pruning (daily at 03:00)
 - HTTP endpoints: health, tail, metrics, on-demand digests
@@ -63,9 +63,9 @@ Runtime modules:
    - Debug logs include: mention delivered or suppression reason (backfill, quiet hours, rate limit)
 
 5) Summarization:
-   - `/trigger` or the scheduler loads a window and calls OpenAI (with a 60s timeout)
+   - `/trigger` or the scheduler loads a window and calls OpenAI
-   - Defaults to `OPENAI_MODEL=gpt-5` with `MaxCompletionTokens`; temperature omitted for reasoning-like models
+   - GPT‑5 context: ~272k input tokens + up to 128k output tokens (400k total)
-   - Tunables let you follow link targets and group multi-line posts (see env below)
+   - Summaries are concise/natural and integrate multi-line posts, article text (readability-extracted), and image links (vision)
 
 6) HTTP API:
    - `/healthz` → `200 ok`
@@ -83,7 +83,7 @@ Runtime modules:
 
 ```yaml
 healthcheck:
-  test: ["/sojuboy", "--health"]
+  test: ["CMD", "/sojuboy", "--health"]
   interval: 30s
   timeout: 3s
   retries: 3
@@ -146,6 +146,8 @@ Compose includes a healthcheck calling the binary’s `--health` flag, which ret
 
 ## Configuration (.env example)
 
+Below shows maximum or large/reasonable values. Defaults are noted where they are also the maximum or when relevant.
+
 ```env
 # soju / IRC
 SOJU_HOST=bnc.example.org
@@ -176,22 +178,25 @@ LLM_PROVIDER=openai
 OPENAI_API_KEY=sk-...
 OPENAI_BASE_URL=https://api.openai.com/v1
 OPENAI_MODEL=gpt-5
-OPENAI_MAX_TOKENS=700
+# Max completion (output) tokens for GPT‑5 is ~128k (model limit). Default 700.
+OPENAI_MAX_TOKENS=128000
 # Summarizer tuning
-SUMM_FOLLOW_LINKS=true           # fetch small snippets from referenced links
+SUMM_FOLLOW_LINKS=true            # default true
-SUMM_LINK_TIMEOUT=6s             # HTTP timeout per link
+SUMM_LINK_TIMEOUT=20s             # no hard max; example large
-SUMM_LINK_MAX_BYTES=262144       # max bytes fetched per link
+SUMM_LINK_MAX_BYTES=1048576       # no hard max; example large (1 MiB/article)
-SUMM_GROUP_WINDOW=90s            # group multi-line posts within this window
+SUMM_GROUP_WINDOW=120s            # no hard max; example large grouping window
-SUMM_MAX_LINKS=5                 # limit links fetched per summary
+SUMM_MAX_LINKS=20                 # no strict max; example large
+SUMM_MAX_GROUPS=20000             # 0=no cap; example large
+SUMM_TIMEOUT=10m                  # request timeout; default 5m
 
 # Digests
-DIGEST_CRON=0 */6 * * *
+DIGEST_CRON=0 */6 * * *           # every 6 hours
-DIGEST_WINDOW=6h
+DIGEST_WINDOW=24h                 # no hard max; example large window
-QUIET_HOURS=
+QUIET_HOURS=                      # e.g., 22:00-07:00
 
 # Mentions/alerts
-NOTIFY_BACKFILL=false             # if true, notify even for replayed (older) messages
+NOTIFY_BACKFILL=false             # default false
-MENTION_MIN_INTERVAL=30s          # min interval between alerts per channel/keyword
+MENTION_MIN_INTERVAL=30s          # no hard max; rate-limit between alerts
 MENTIONS_ONLY_CHANNELS=           # optional allow-list (CSV)
 MENTIONS_DENY_CHANNELS=           # optional deny-list (CSV)
 URGENT_KEYWORDS=urgent,priority   # bypass quiet hours
@@ -202,7 +207,7 @@ HTTP_TOKEN=put-a-long-random-token-here
 
 # Storage
 STORE_PATH=/data/app.db
-STORE_RETENTION_DAYS=7
+STORE_RETENTION_DAYS=365          # example large retention
 
 # Logging
 LOG_LEVEL=info
@@ -220,7 +225,7 @@ LOG_LEVEL=info
 - Set `OPENAI_API_KEY`
 - Set `OPENAI_BASE_URL` to exactly `https://api.openai.com/v1`
 - If `gpt-5` isn’t available on your account, use a supported model like `gpt-4o-mini`
-- GPT-5 beta limitations: temperature fixed; use `MaxCompletionTokens`
+- GPT‑5 limits: ~272k input + 128k output tokens (400k context)
 
 ## HTTP API
 

cmd/sojuboy/main.go

@@ -108,16 +108,15 @@ func main() {
 
 	// HTTP API
 	api := httpapi.Server{
-		ListenAddr: cfg.HTTPListen,
+		ListenAddr:        cfg.HTTPListen,
-		AuthToken:  cfg.HTTPToken,
+		AuthToken:         cfg.HTTPToken,
-		Store:      st,
+		Store:             st,
-		Summarizer: sum,
+		Summarizer:        sum,
-		Notifier:   nt,
+		Notifier:          nt,
-		Logger:     slog.New(slog.NewJSONHandler(os.Stdout, nil)), // legacy interface still expects *log.Logger; keep minimal text via adapter if needed
+		Logger:            slog.New(slog.NewJSONHandler(os.Stdout, nil)),
-		Metrics:    metrics,
+		Metrics:           metrics,
-		Ready: func() bool {
+		Ready:             func() bool { return atomic.LoadInt64(&metrics.ConnectedGauge) == 1 },
-			return atomic.LoadInt64(&metrics.ConnectedGauge) == 1
+		SummarizerTimeout: cfg.SummarizerTimeout,
-		},
 	}
 	go func() {
 		if err := api.Start(ctx); err != nil && err != http.ErrServerClosed {

go.mod

@@ -5,6 +5,7 @@ go 1.23.0
 toolchain go1.24.6
 
 require (
+	github.com/go-shiori/go-readability v0.0.0-20250217085726-9f5bf5ca7612
 	github.com/gregdel/pushover v1.3.1
 	github.com/robfig/cron/v3 v3.0.1
 	github.com/sashabaranov/go-openai v1.41.1
@@ -13,13 +14,19 @@ require (
 )
 
 require (
+	github.com/andybalholm/cascadia v1.3.3 // indirect
+	github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
+	github.com/go-shiori/dom v0.0.0-20230515143342-73569d674e1c // indirect
+	github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/ncruces/go-strftime v0.1.9 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
+	golang.org/x/net v0.35.0 // indirect
 	golang.org/x/sys v0.34.0 // indirect
+	golang.org/x/text v0.22.0 // indirect
 	modernc.org/libc v1.66.3 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect

go.sum

@@ -1,5 +1,19 @@
+github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
+github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
+github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de h1:FxWPpzIjnTlhPwqqXc4/vE0f7GvRjuAsbW+HOIe8KnA=
+github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de/go.mod h1:DCaWoUhZrYW9p1lxo/cm8EmUOOzAPSEZNGF2DK1dJgw=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+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/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
+github.com/go-shiori/dom v0.0.0-20230515143342-73569d674e1c h1:wpkoddUomPfHiOziHZixGO5ZBS73cKqVzZipfrLmO1w=
+github.com/go-shiori/dom v0.0.0-20230515143342-73569d674e1c/go.mod h1:oVDCh3qjJMLVUSILBRwrm+Bc6RNXGZYtoh9xdvf1ffM=
+github.com/go-shiori/go-readability v0.0.0-20250217085726-9f5bf5ca7612 h1:BYLNYdZaepitbZreRIa9xeCQZocWmy/wj4cGIH0qyw0=
+github.com/go-shiori/go-readability v0.0.0-20250217085726-9f5bf5ca7612/go.mod h1:wgqthQa8SAYs0yyljVeCOQlZ027VW5CmLsbi9jWC08c=
+github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f h1:3BSP1Tbs2djlpprl7wCLuiqMaUh5SJkkzI2gDs+FgLs=
+github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f/go.mod h1:Pcatq5tYkCW2Q6yrR2VRHlbHpZ/R4/7qyL1TCF7vl14=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e h1:ijClszYn+mADRFY17kjQEVQ1XRhq2/JR1M3sGqeJoxs=
 github.com/google/pprof v0.0.0-20250317173921-a4b03ec1a45e/go.mod h1:boTsfXsheKC2y+lKOCMpSfarhxDeIzfZG1jqGcPl3cA=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
@@ -8,27 +22,109 @@ github.com/gregdel/pushover v1.3.1 h1:4bMLITOZ15+Zpi6qqoGqOPuVHCwSUvMCgVnN5Xhilf
 github.com/gregdel/pushover v1.3.1/go.mod h1:EcaO66Nn1StkpEm1iKtBTV3d2A16SoMsVER1PthX7to=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+github.com/mattn/go-runewidth v0.0.10/go.mod h1:RAqKPSqVFrSLVXbA8x7dzmKdmGzieGRCM46jaSJTDAk=
 github.com/ncruces/go-strftime v0.1.9 h1:bY0MQC28UADQmHmaF5dgpLmImcShSi2kHU9XLdhx/f4=
 github.com/ncruces/go-strftime v0.1.9/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/rivo/uniseg v0.1.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
 github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
 github.com/sashabaranov/go-openai v1.41.1 h1:zf5tM+GuxpyiyD9XZg8nCqu52eYFQg9OOew0gnIuDy4=
 github.com/sashabaranov/go-openai v1.41.1/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
+github.com/scylladb/termtables v0.0.0-20191203121021-c4c0b6d42ff4/go.mod h1:C1a7PQSMz9NShzorzCiG2fk9+xuCgLkPeCvMHYR2OWg=
+github.com/sergi/go-diff v1.1.0 h1:we8PVUC3FE2uYfodKH/nBHMSetSfHDR6scGdBi+erh0=
+github.com/sergi/go-diff v1.1.0/go.mod h1:STckp+ISIX8hZLjrqAeVduY0gWCT9IjLuqbuNXdaHfM=
 github.com/sorcix/irc v1.1.4 h1:KDmVMPPzK4kbf3TQw1RsZAqTsh2JL9Zw69hYduX9Ykw=
 github.com/sorcix/irc v1.1.4/go.mod h1:MhzbySH63tDknqfvAAFK3ps/942g4z9EeJ/4lGgHyZc=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
+golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
+golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
+golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
 golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
 golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
+golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/mod v0.25.0 h1:n7a+ZbQKQA/Ysbyb0/6IbB1H/X41mKgbhfv7AfG/44w=
 golang.org/x/mod v0.25.0/go.mod h1:IXM97Txy2VM4PJ3gI61r1YEk/gAj6zAHN3AdZt6S9Ww=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
+golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
+golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
+golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
+golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
+golang.org/x/net v0.35.0 h1:T5GQRQb2y08kTAByq9L4/bz8cipCdA8FbRTXewonqY8=
+golang.org/x/net v0.35.0/go.mod h1:EglIi67kWsHKlRzzVMUD93VMSWGFOMSZgxFjparz1Qk=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
+golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sync v0.15.0 h1:KWH3jNZsfyT6xfAfKiz6MRNmd46ByHDYaZ7KSkCtdW8=
 golang.org/x/sync v0.15.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.34.0 h1:H5Y5sJ2L2JRdyv7ROF1he/lPdvFsd0mJHFw2ThKHxLA=
 golang.org/x/sys v0.34.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
+golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
+golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
+golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
+golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
+golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
+golang.org/x/text v0.22.0 h1:bofq7m3/HAFvbF51jz3Q9wLg3jkvSPuiZu/pD1XwgtM=
+golang.org/x/text v0.22.0/go.mod h1:YRoo4H8PVmsu+E3Ou7cqLVH8oXWIHVoX0jqUWALQhfY=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
+golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
+golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
 golang.org/x/tools v0.34.0 h1:qIpSLOxeCYGg9TrcJokLBG4KFA6d795g0xkBkiESGlo=
 golang.org/x/tools v0.34.0/go.mod h1:pAP9OwEaY1CAW3HOmg3hLZC5Z0CCmzjAF2UQMSqNARg=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 modernc.org/cc/v4 v4.26.2 h1:991HMkLjJzYBIfha6ECZdjrIYz2/1ayr+FL8GN+CNzM=
 modernc.org/cc/v4 v4.26.2/go.mod h1:uVtb5OGqUKpoLWhqwNQo/8LwvoiEBLvZXIQ/SmO6mL0=
 modernc.org/ccgo/v4 v4.28.0 h1:rjznn6WWehKq7dG4JtLRKxb52Ecv8OUGah8+Z/SfpNU=

internal/config/config.go

@@ -28,16 +28,18 @@ type Config struct {
 	PushoverAPIToken string
 
 	// Summarizer / LLM
-	LLMProvider      string
+	LLMProvider       string
-	OpenAIAPIKey     string
+	OpenAIAPIKey      string
-	OpenAIBaseURL    string
+	OpenAIBaseURL     string
-	OpenAIModel      string
+	OpenAIModel       string
-	OpenAIMaxTokens  int
+	OpenAIMaxTokens   int
-	SummFollowLinks  bool
+	SummFollowLinks   bool
-	SummLinkTimeout  time.Duration
+	SummLinkTimeout   time.Duration
-	SummLinkMaxBytes int
+	SummLinkMaxBytes  int
-	SummGroupWindow  time.Duration
+	SummGroupWindow   time.Duration
-	SummMaxLinks     int
+	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)

internal/httpapi/server.go

@@ -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.
+	// Timeout summarization using configurable timeout (default 5m)
-	ctxSum, cancel := context.WithTimeout(ctx, 60*time.Second)
+	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 {

internal/summarizer/openai.go

@@ -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 {
+	// Split image vs non-image
-		links = fetchLinkSnippets(ctx, links, o.linkTimeout, o.linkMaxBytes, o.maxLinks)
+	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 {
+			if len(text) > 2000 {
-				text = text[:800]
+				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)
+}