Local fork: hardening + ops improvements (timeout knob, demotion, /livez, drain)

This commit captures both the prior accumulated work-in-progress
(framework migration web/→svelte/, postgres storage, conversation
viewer, dashboard auth, OpenAPI spec, integration tests) AND today's
operational improvements layered on top. History wasn't checkpointed
incrementally; happy to split it via interactive rebase if a reviewer
wants smaller commits.

Today's changes (in addition to the older WIP):

1. Configurable upstream response-header timeout
   - ANTHROPIC_RESPONSE_HEADER_TIMEOUT env (default 300s)
   - Replaces hardcoded 300s in provider/anthropic.go that was firing
     on opus + 1M-context + extended thinking non-streaming requests
   - Files: internal/config/config.go, internal/provider/anthropic.go

2. Structured forward-error diagnostic logging
   - When a forward to Anthropic fails, log a single key=value line
     with request_id, model, stream, body_bytes, has_thinking,
     anthropic_beta, query, elapsed, ctx_err — alongside the existing
     human-readable error line for back-compat
   - Files: internal/handler/handlers.go (logForwardFailure)

3. Full SSE protocol passthrough + Flusher fix
   - handler/handlers.go: forward all SSE lines verbatim (event:, id:,
     retry:, : comments, blank-line terminators), not only data:.
     Previous code produced malformed SSE for strict parsers.
   - middleware/logging.go: explicit Flush() method on responseWriter.
     Embedding http.ResponseWriter (interface) does not auto-promote
     Flush(), so every w.(http.Flusher) check in the streaming
     handler was returning ok=false and SSE writes buffered in net/http
     until the body closed.

4. Non-streaming → streaming demotion (feature-flagged)
   - ANTHROPIC_DEMOTE_NONSTREAMING env (default false)
   - When enabled and the routed provider is anthropic, force stream=true
     upstream for clients that asked for stream=false. Receive SSE,
     accumulate via accumulateSSEToMessage (handles text, tool_use with
     partial_json reassembly, thinking, signature, citations_delta,
     usage merge), and synthesize a single non-streaming JSON response.
   - Eliminates the ResponseHeaderTimeout class of failure entirely.
   - Body rewrite uses json.Decoder + UseNumber() to preserve integer
     precision in unknown nested fields (tool inputs from prior turns).
   - Files: internal/config/config.go, internal/handler/handlers.go,
     cmd/proxy/main.go, cmd/proxy/main_test.go

5. Live operational state: /livez gauge + graceful drain
   - New internal/runtime package: atomic in-flight counter + draining flag
   - New middleware/inflight.go: increments runtime gauge, applied to
     /v1/* subrouter so Messages, ChatCompletions, and ProxyPassthrough
     are all counted
   - /v1/* moved to a gorilla/mux subrouter so the InFlight middleware
     applies surgically; /health, /livez, /openapi.* remain on parent
     router (unauthenticated, uncounted)
   - Health handler returns 503 draining when runtime.IsDraining() is
     true, so Traefik stops routing to a slot before drain begins
   - New /livez handler returns {status, in_flight, draining, timestamp}
   - SIGTERM handler in main.go: SetDraining(true), poll for in_flight==0
     with 32-min ceiling and 1s tick (logs every 10s), then srv.Shutdown
   - Auth bypass list extended with /livez
   - Files: internal/runtime/runtime.go (new),
     internal/middleware/inflight.go (new),
     internal/middleware/auth.go,
     internal/handler/handlers.go (Health, Livez, runtime import),
     cmd/proxy/main.go (subrouter, drain loop)

6. OpenAPI spec updates
   - Document Health 503 response and new DrainingResponse schema
   - Add /livez path with LivezResponse schema
   - Files: internal/handler/openapi.go

Verified: go build ./... clean, go test ./... all pass, go vet clean.
Three rounds of codex peer review across changes 1-5; all feedback
addressed (citations_delta, json.Number precision, drain-loop logging
via lastLog timestamp, PathPrefix tightened to "/v1/").

run.sh

@@ -1,10 +1,10 @@
 #!/bin/bash
 
-# Claude Code Monitor - Build and Run Script
+# Claude Code Proxy - Build and Run Script
 
 set -e
 
-echo "🚀 Claude Code Monitor - Starting Services"
+echo "🚀 Claude Code Proxy - Starting Services"
 echo "========================================="
 
 # Colors for output
@@ -40,7 +40,7 @@ fi
 # Function to cleanup on exit
 cleanup() {
     echo -e "\n${YELLOW}Shutting down services...${NC}"
-    kill $PROXY_PID $WEB_PID 2>/dev/null || true
+    kill $PROXY_PID $SVELTE_PID 2>/dev/null || true
     exit
 }
 
@@ -55,13 +55,13 @@ cd ..
 
 echo -e "${GREEN}✅ Proxy server built${NC}"
 
-# Install web dependencies if needed
-if [ ! -d "web/node_modules" ]; then
-    echo -e "\n${BLUE}📦 Installing web dependencies...${NC}"
-    cd web
+# Install svelte dependencies if needed
+if [ ! -d "svelte/node_modules" ]; then
+    echo -e "\n${BLUE}📦 Installing svelte dependencies...${NC}"
+    cd svelte
     npm install
     cd ..
-    echo -e "${GREEN}✅ Web dependencies installed${NC}"
+    echo -e "${GREEN}✅ Svelte dependencies installed${NC}"
 fi
 
 # Start proxy server
@@ -72,20 +72,20 @@ PROXY_PID=$!
 # Wait for proxy to start
 sleep 2
 
-# Start web server
-echo -e "${BLUE}🚀 Starting web interface on port 5173...${NC}"
-cd web
+# Start svelte server
+echo -e "${BLUE}🚀 Starting Svelte Dashboard on port 5174...${NC}"
+cd svelte
 npm run dev &
-WEB_PID=$!
+SVELTE_PID=$!
 cd ..
 
 echo -e "\n${GREEN}✨ All services started!${NC}"
 echo "========================================="
-echo -e "📊 Web Dashboard: ${BLUE}http://localhost:5173${NC}"
+echo -e "📊 Svelte Dashboard: ${BLUE}http://localhost:5174${NC}"
 echo -e "🔌 API Proxy: ${BLUE}http://localhost:3001${NC}"
 echo -e "💚 Health Check: ${BLUE}http://localhost:3001/health${NC}"
 echo "========================================="
 echo -e "${YELLOW}Press Ctrl+C to stop all services${NC}\n"
 
 # Wait for processes
-wait
+wait