refactor(server): drop stale prompt text, duplicated routes and dead options

- lib/system-prompts.ts: delete the extended prompt kept only to reach
  the 4096-token cache threshold of two old Claude models; describe the
  current canvas-first UI in the App Features section
- app/api/chat/route.ts: remove the server-side example cache (the
  browser answers examples itself), the ENABLE_HISTORY_XML_REPLACE
  option and its helper, the unread messageMetadata fields; the
  DEBUG_LLM_PAYLOAD blocks become one describeMessages summary
- app/api/log-feedback and log-save share scoreLatestTrace in
  lib/langfuse.ts
- app/api/admin/test-model and validate-model call a shared
  testModelConnection() instead of one route faking a request to the
  other and passing trust through the body
- lib/dynamo-quota-manager.ts reads the failing item from the
  conditional update instead of a second GetItem
- lib/ai-providers.ts: geminiThinkingOptions helper for the google and
  vertexai cases, drop the unused fourth resolveBaseURL parameter
- edge-functions: always stream, shrink messageSchema, drop model
  aliases nothing sends
- delete app/api/chat/xml_guide.md, parseOutputTokenLimit, unused type
  exports and export keywords on file-internal symbols
- env.example: drop variables nothing reads, document the quota,
  validation and analytics variables, mention the apiKeyEnv array form
  (also in docs/*/ai-providers.md)

lib/test-model-connection.ts

@@ -0,0 +1,239 @@
+import { streamText, tool } from "ai"
+import { NextResponse } from "next/server"
+import { z } from "zod"
+import {
+    edgeOneEndpoint,
+    getAIModel,
+    usesServerCredentials,
+    usesServerEndpoint,
+} from "@/lib/ai-providers"
+import {
+    checkAndIncrementRequest,
+    isQuotaEnabled,
+} from "@/lib/dynamo-quota-manager"
+import { classifyLLMError } from "@/lib/llm-errors"
+import { allowPrivateUrls, isPrivateUrl } from "@/lib/ssrf-protection"
+import { normalizeBaseUrl, type ProviderName } from "@/lib/types/model-config"
+import { getUserIdFromRequest } from "@/lib/user-id"
+
+export interface TestModelRequest {
+    provider: ProviderName
+    apiKey?: string
+    baseUrl?: string
+    modelId: string
+    // AWS Bedrock specific
+    awsAccessKeyId?: string
+    awsSecretAccessKey?: string
+    awsRegion?: string
+    awsSessionToken?: string
+    // Vertex AI specific
+    vertexApiKey?: string // Express Mode API key
+}
+
+const TEST_TIMEOUT_MS = 15_000
+
+// Drawing works through tool calls, so the test asks for one
+const PING_TOOL = tool({
+    description: "Report that the connection works.",
+    inputSchema: z.object({}),
+})
+
+const NO_TOOL_CALL_WARNING =
+    "Connected, but the model answered without calling a tool. It may not support tool calls, which drawing needs."
+
+/**
+ * Run one tool call on a model, as the chat would, and report the result.
+ * Shared by the Settings dialog's Test (/api/validate-model) and the admin
+ * panel's Test (/api/admin/test-model). req supplies the EdgeOne endpoint,
+ * cookies, access code and the user id for the quota. trustedBaseUrl marks
+ * body.baseUrl as the server's own <P>_BASE_URL (the admin panel's Test of
+ * an entry without a URL), not one a user typed: chat uses it as it is, so
+ * no private-address or redirect rules, and no quota.
+ */
+export async function testModelConnection(
+    req: Request,
+    body: TestModelRequest,
+    trustedBaseUrl: boolean,
+): Promise<NextResponse> {
+    try {
+        const {
+            provider,
+            apiKey,
+            modelId,
+            awsAccessKeyId,
+            awsSecretAccessKey,
+            awsRegion,
+            awsSessionToken,
+            // Note: Express Mode only needs vertexApiKey
+            vertexApiKey,
+        } = body
+
+        if (!provider || !modelId) {
+            return NextResponse.json(
+                { valid: false, error: "Provider and model ID are required" },
+                { status: 400 },
+            )
+        }
+        // EdgeOne is this site's own function, as in the chat; the admin
+        // panel's Test sends no URL, and a relative one cannot be fetched
+        const baseUrl =
+            provider === "edgeone" ? edgeOneEndpoint(req) : body.baseUrl
+
+        // SECURITY: Block SSRF attacks via custom baseUrl
+        if (
+            baseUrl &&
+            !trustedBaseUrl &&
+            !allowPrivateUrls() &&
+            (await isPrivateUrl(baseUrl))
+        ) {
+            return NextResponse.json(
+                { valid: false, error: "Invalid base URL" },
+                { status: 400 },
+            )
+        }
+
+        // Validate credentials based on provider
+        if (provider === "bedrock") {
+            if (
+                !(apiKey || (awsAccessKeyId && awsSecretAccessKey)) ||
+                !awsRegion
+            ) {
+                return NextResponse.json(
+                    {
+                        valid: false,
+                        error: "AWS credentials (a Bedrock API key, or an Access Key ID and Secret Access Key, and a Region) are required",
+                    },
+                    { status: 400 },
+                )
+            }
+        } else if (provider === "vertexai") {
+            if (!vertexApiKey) {
+                return NextResponse.json(
+                    {
+                        valid: false,
+                        error: "Vertex AI API key is required for Express Mode",
+                    },
+                    { status: 400 },
+                )
+            }
+        } else if (provider !== "ollama" && provider !== "edgeone" && !apiKey) {
+            return NextResponse.json(
+                { valid: false, error: "API key is required" },
+                { status: 400 },
+            )
+        }
+        // The Test button checks the user's own provider. On the server's
+        // keys (Ollama Cloud without a key or URL) anyone could run any model.
+        if (
+            usesServerCredentials(provider, {
+                apiKey,
+                baseUrl,
+                awsAccessKeyId,
+                awsSecretAccessKey,
+                vertexApiKey,
+            })
+        ) {
+            return NextResponse.json(
+                { valid: false, error: "API key is required" },
+                { status: 400 },
+            )
+        }
+
+        // On the deployment's own endpoints a Test runs a model as a chat
+        // does, so with the quota on it counts as a chat request (an
+        // admin's Test of the server's URL does not)
+        const userId = getUserIdFromRequest(req)
+        if (
+            isQuotaEnabled() &&
+            !trustedBaseUrl &&
+            userId !== "anonymous" &&
+            (await usesServerEndpoint(
+                provider,
+                normalizeBaseUrl(body.baseUrl ?? ""),
+                apiKey,
+            ))
+        ) {
+            const quotaCheck = await checkAndIncrementRequest(userId, {
+                requests: Number(process.env.DAILY_REQUEST_LIMIT) || 10,
+                tokens: Number(process.env.DAILY_TOKEN_LIMIT) || 200000,
+                tpm: Number(process.env.TPM_LIMIT) || 20000,
+            })
+            if (!quotaCheck.allowed) {
+                return NextResponse.json(
+                    { valid: false, error: quotaCheck.error },
+                    { status: 429 },
+                )
+            }
+        }
+
+        // The same model the chat would use. A client base URL makes it
+        // refuse redirects to internal hosts.
+        const { model } = getAIModel({
+            provider,
+            modelId,
+            apiKey,
+            baseUrl,
+            trustedBaseUrl,
+            awsAccessKeyId,
+            awsSecretAccessKey,
+            awsRegion,
+            // Temporary AWS credentials need it, as in the chat
+            awsSessionToken,
+            vertexApiKey,
+            // EdgeOne checks the Pages cookies and the access code
+            ...(provider === "edgeone" && {
+                headers: {
+                    cookie: req.headers.get("cookie") || "",
+                    "x-access-code": req.headers.get("x-access-code") || "",
+                },
+            }),
+        })
+
+        // Streaming, like the chat (some models only stream). Stop at the
+        // first tool call; a reasoning model that runs out of tokens first
+        // proves the connection but not tool support.
+        const startTime = Date.now()
+        const result = streamText({
+            model,
+            prompt: "Call the ping tool.",
+            tools: { ping: PING_TOOL },
+            maxOutputTokens: 1024,
+            maxRetries: 0,
+            abortSignal: AbortSignal.timeout(TEST_TIMEOUT_MS),
+        })
+        let calledTool = false
+        let finishReason: string | undefined
+        for await (const part of result.fullStream) {
+            if (part.type === "error") throw part.error
+            // The timeout ends the stream with an abort part, not an error
+            if (part.type === "abort") {
+                const timeout = new Error(
+                    `The model did not answer within ${TEST_TIMEOUT_MS / 1000} s.`,
+                )
+                timeout.name = "TimeoutError"
+                throw timeout
+            }
+            if (part.type === "tool-call") {
+                calledTool = true
+                break
+            }
+            if (part.type === "finish") finishReason = part.finishReason
+        }
+        const responseTime = Date.now() - startTime
+
+        return NextResponse.json({
+            valid: true,
+            responseTime,
+            ...(!calledTool &&
+                finishReason !== "length" && { warning: NO_TOOL_CALL_WARNING }),
+        })
+    } catch (error) {
+        console.error("[validate-model] Error:", error)
+
+        const { code, message } = classifyLLMError(error)
+        return NextResponse.json(
+            { valid: false, code, error: message },
+            { status: 200 }, // Return 200 so client can read error message
+        )
+    }
+}