fix(scriberr): patch 0004 — chat context window for gateway model names (LLM_DEFAULT_CONTEXT_WINDOW=131072); image ctxwin1 live, idle-gated deploy; svos v0.0.20 staged

stacks/scriberr/.env.example

@@ -54,3 +54,6 @@ SCRIBERR_SECURE_COOKIES=false
 # when unset; override only with a re-measured peak.
 # SCRIBERR_PARAKEET_CHUNK_SECS=120
 # SCRIBERR_PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+
+# Chat context window for gateway model names (patch 0004; needs an image built with it).
+# SCRIBERR_LLM_DEFAULT_CONTEXT_WINDOW=131072

stacks/scriberr/compose.yaml

@@ -65,6 +65,10 @@ services:
       # reached by host IP. Keep this in sync with how the app is reached.
       - ALLOWED_ORIGINS=${SCRIBERR_ALLOWED_ORIGINS}
       - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+      # Chat's context window for a model name Scriberr's OpenAI table does not know (patch 0004, 2026-10-19).
+      # Upstream returns 4096 for every non-OpenAI name, so chat refused any transcript over ~3.6k estimated
+      # tokens even on 262k-context gateway models (summarizer, gen-large). Half their real context.
+      - LLM_DEFAULT_CONTEXT_WINDOW=${SCRIBERR_LLM_DEFAULT_CONTEXT_WINDOW:-131072}
       # Scriberr builds each model backend's Python env with `uv` at runtime.
       # uv's default link mode reflink/hardlinks out of its cache, which fails
       # on this overlayfs+ZFS combination with a misleading

stacks/scriberr/patches/0004-chat-default-context-window-env.patch

@@ -0,0 +1,35 @@
+Subject: [PATCH 0004] chat: LLM_DEFAULT_CONTEXT_WINDOW for model names the OpenAI table does not know
+
+OpenAIService.GetContextWindow knows only OpenAI's own names (gpt-4o, gpt-4, gpt-3.5)
+and returns 4096 for anything else. Behind an OpenAI-compatible gateway every model is
+"anything else" (here LiteLLM's summarizer and gen-large, 262k-context vLLM seats), so
+chat refuses any transcript the handler estimates above 3,596 tokens (chars/4, minus 500
+kept for the reply): a 22k-character meeting was refused on 2026-10-19 with "limit 4096".
+The default branch now reads LLM_DEFAULT_CONTEXT_WINDOW (a positive integer) and keeps
+4096 when it is unset or invalid; the known OpenAI names are unchanged.
+
+---
+--- a/internal/llm/openai.go
++++ b/internal/llm/openai.go
+@@ -9,6 +9,8 @@
+ 	"io"
+ 	"log"
+ 	"net/http"
++	"os"
++	"strconv"
+ 	"strings"
+ 	"time"
+ )
+@@ -337,7 +339,11 @@
+ 	case strings.HasPrefix(model, "gpt-3.5-turbo"):
+ 		return 16385, nil // Most recent gpt-3.5-turbo is 16k
+ 	default:
+-		// Default fallback
++		// Not an OpenAI model name (a LiteLLM alias, a vLLM served name): the operator's
++		// LLM_DEFAULT_CONTEXT_WINDOW when set to a positive integer, else upstream's 4096.
++		if v, err := strconv.Atoi(strings.TrimSpace(os.Getenv("LLM_DEFAULT_CONTEXT_WINDOW"))); err == nil && v > 0 {
++			return v, nil
++		}
+ 		return 4096, nil
+ 	}
+ }