fix: ?no-history flag and improve /logs monitoring docs (#721)

- improve logging documentation 
- small tweaks for edge case issues in upstream and log requests

README.md

@@ -20,6 +20,7 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
   - `v1/chat/completions`
   - `v1/responses`
   - `v1/embeddings`
+  - `v1/models` - list available models
   - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
   - `v1/audio/transcriptions` ([docs](https://github.com/mostlygeek/llama-swap/issues/41#issuecomment-2722637867))
   - `v1/audio/voices`
@@ -39,9 +40,17 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
 - ✅ llama-swap API
   - `/ui` - web UI
   - `/upstream/:model_id` - direct access to upstream server ([demo](https://github.com/mostlygeek/llama-swap/pull/31))
-  - `/models/unload` - manually unload running models ([#58](https://github.com/mostlygeek/llama-swap/issues/58))
   - `/running` - list currently running models ([#61](https://github.com/mostlygeek/llama-swap/issues/61))
-  - `/log` - remote log monitoring
+  - `POST /api/models/unload` - manually unload all running models ([#58](https://github.com/mostlygeek/llama-swap/issues/58))
+  - `POST /api/models/unload/:model_id` - unload a specific model
+  - `/logs` - remote log monitoring
+    - `GET /logs` returns buffered plain text logs.
+      - If `Accept: text/html` is sent, `/logs` redirects to `/ui/`.
+    - `GET /logs/stream` keeps the connection open for live log streaming.
+      - Stream endpoints send buffered history first by default; add `?no-history` to stream only new lines.
+    - `GET /logs/stream/proxy` streams proxy logs only.
+    - `GET /logs/stream/upstream` streams upstream process logs only.
+    - `GET /logs/stream/{model_id}` streams logs for one model (including IDs with slashes, like `author/model`).
   - `/health` - just returns "OK"
 - ✅ API Key support - define keys to restrict access to API endpoints
 - ✅ Customizable

proxy/proxymanager.go

@@ -683,7 +683,7 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 	searchModelName, modelID, remainingPath, modelFound := pm.findModelInPath(upstreamPath)
 
 	if !modelFound {
-		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
+		pm.sendErrorResponse(c, http.StatusNotFound, "model not found")
 		return
 	}
 

proxy/proxymanager_loghandlers.go

@@ -32,6 +32,13 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 	c.Header("X-Accel-Buffering", "no")
 
 	logMonitorId := strings.TrimPrefix(c.Param("logMonitorID"), "/")
+
+	// Handle case where query string might be included in the parameter
+	// (can happen with catch-all routes on some versions/setups)
+	if idx := strings.Index(logMonitorId, "?"); idx != -1 {
+		logMonitorId = logMonitorId[:idx]
+	}
+
 	logger, err := pm.getLogger(logMonitorId)
 	if err != nil {
 		c.String(http.StatusBadRequest, err.Error())

proxy/proxymanager_loghandlers_test.go

@@ -0,0 +1,49 @@
+package proxy
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestLogMonitorIdQueryParameterStripping(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected string
+	}{
+		{
+			name:     "upstream without query param",
+			input:    "upstream",
+			expected: "upstream",
+		},
+		{
+			name:     "upstream with query param",
+			input:    "upstream?no-history",
+			expected: "upstream",
+		},
+		{
+			name:     "proxy with multiple query params",
+			input:    "proxy?no-history&foo=bar",
+			expected: "proxy",
+		},
+		{
+			name:     "model with slash and query param",
+			input:    "author/model?no-history",
+			expected: "author/model",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Simulate the query parameter stripping logic
+			logMonitorId := tt.input
+			if idx := strings.Index(logMonitorId, "?"); idx != -1 {
+				logMonitorId = logMonitorId[:idx]
+			}
+
+			if logMonitorId != tt.expected {
+				t.Errorf("Query parameter stripping failed: got %q, want %q", logMonitorId, tt.expected)
+			}
+		})
+	}
+}