@blockrun/clawrouter 0.12.63 → 0.12.65

package/README.md

@@ -108,11 +108,11 @@ Choose your routing strategy with `/model <profile>`:
 Request → Weighted Scorer (15 dimensions) → Tier → Best Model → Response
 ```
 
-| Tier      | ECO Model                           | AUTO Model                         | PREMIUM Model                |
-| --------- | ----------------------------------- | ---------------------------------- | ---------------------------- |
-| SIMPLE    | nvidia/gpt-oss-120b (FREE)          | kimi-k2.5 ($0.60/$3.00)            | kimi-k2.5                    |
-| MEDIUM    | gemini-2.5-flash-lite ($0.10/$0.40) | grok-4-0709 ($0.20/$1.50)          | gpt-5.3-codex ($1.75/$14.00) |
-| COMPLEX   | gemini-2.5-flash-lite ($0.10/$0.40) | gemini-3.1-pro ($2/$12)            | claude-opus-4.6 ($5/$25)     |
+| Tier      | ECO Model                           | AUTO Model                            | PREMIUM Model                |
+| --------- | ----------------------------------- | ------------------------------------- | ---------------------------- |
+| SIMPLE    | nvidia/gpt-oss-120b (FREE)          | kimi-k2.5 ($0.60/$3.00)               | kimi-k2.5                    |
+| MEDIUM    | gemini-2.5-flash-lite ($0.10/$0.40) | grok-4-0709 ($0.20/$1.50)             | gpt-5.3-codex ($1.75/$14.00) |
+| COMPLEX   | gemini-2.5-flash-lite ($0.10/$0.40) | gemini-3.1-pro ($2/$12)               | claude-opus-4.6 ($5/$25)     |
 | REASONING | grok-4-fast ($0.20/$0.50)           | grok-4-1-fast-reasoning ($0.20/$0.50) | claude-sonnet-4.6 ($3/$15)   |
 
 **Blended average: $2.05/M** vs $25/M for Claude Opus = **92% savings**
@@ -165,62 +165,62 @@ Edit existing images with `/img2img`:
 
 ### Budget Models (under $0.001/request)
 
-| Model | Input $/M | Output $/M | ~$/request | Context | Features |
-| --- | ---: | ---: | ---: | --- | --- |
-| nvidia/gpt-oss-120b | **FREE** | **FREE** | **$0** | 128K | |
-| openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
-| openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
-| google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
-| openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
-| xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
-| xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
-| xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
-| xai/grok-4-1-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
-| xai/grok-4-0709 | $0.20 | $1.50 | $0.0009 | 131K | reasoning, tools |
-| openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
-| deepseek/deepseek-chat | $0.28 | $0.42 | $0.0004 | 128K | tools |
-| deepseek/deepseek-reasoner | $0.28 | $0.42 | $0.0004 | 128K | reasoning, tools |
-| xai/grok-3-mini | $0.30 | $0.50 | $0.0004 | 131K | tools |
-| minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
-| minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
-| google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
-| openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
-| google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
-| nvidia/kimi-k2.5 | $0.55 | $2.50 | $0.0015 | 262K | tools |
-| moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
+| Model                         | Input $/M | Output $/M | ~$/request | Context | Features                          |
+| ----------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- |
+| nvidia/gpt-oss-120b           |  **FREE** |   **FREE** |     **$0** | 128K    |                                   |
+| openai/gpt-5-nano             |     $0.05 |      $0.40 |    $0.0002 | 128K    | tools                             |
+| openai/gpt-4.1-nano           |     $0.10 |      $0.40 |    $0.0003 | 128K    | tools                             |
+| google/gemini-2.5-flash-lite  |     $0.10 |      $0.40 |    $0.0003 | 1M      | tools                             |
+| openai/gpt-4o-mini            |     $0.15 |      $0.60 |    $0.0004 | 128K    | tools                             |
+| xai/grok-4-fast               |     $0.20 |      $0.50 |    $0.0004 | 131K    | tools                             |
+| xai/grok-4-fast-reasoning     |     $0.20 |      $0.50 |    $0.0004 | 131K    | reasoning, tools                  |
+| xai/grok-4-1-fast             |     $0.20 |      $0.50 |    $0.0004 | 131K    | tools                             |
+| xai/grok-4-1-fast-reasoning   |     $0.20 |      $0.50 |    $0.0004 | 131K    | reasoning, tools                  |
+| xai/grok-4-0709               |     $0.20 |      $1.50 |    $0.0009 | 131K    | reasoning, tools                  |
+| openai/gpt-5-mini             |     $0.25 |      $2.00 |    $0.0011 | 200K    | tools                             |
+| deepseek/deepseek-chat        |     $0.28 |      $0.42 |    $0.0004 | 128K    | tools                             |
+| deepseek/deepseek-reasoner    |     $0.28 |      $0.42 |    $0.0004 | 128K    | reasoning, tools                  |
+| xai/grok-3-mini               |     $0.30 |      $0.50 |    $0.0004 | 131K    | tools                             |
+| minimax/minimax-m2.7          |     $0.30 |      $1.20 |    $0.0008 | 205K    | reasoning, agentic, tools         |
+| minimax/minimax-m2.5          |     $0.30 |      $1.20 |    $0.0008 | 205K    | reasoning, agentic, tools         |
+| google/gemini-2.5-flash       |     $0.30 |      $2.50 |    $0.0014 | 1M      | vision, tools                     |
+| openai/gpt-4.1-mini           |     $0.40 |      $1.60 |    $0.0010 | 128K    | tools                             |
+| google/gemini-3-flash-preview |     $0.50 |      $3.00 |    $0.0018 | 1M      | vision                            |
+| nvidia/kimi-k2.5              |     $0.55 |      $2.50 |    $0.0015 | 262K    | tools                             |
+| moonshot/kimi-k2.5            |     $0.60 |      $3.00 |    $0.0018 | 262K    | reasoning, vision, agentic, tools |
 
 ### Mid-Range Models ($0.001–$0.01/request)
 
-| Model | Input $/M | Output $/M | ~$/request | Context | Features |
-| --- | ---: | ---: | ---: | --- | --- |
-| anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $0.0030 | 200K | vision, agentic, tools |
-| zai/glm-5 | $1.00 | $3.20 | $0.0021 | 200K | tools |
-| openai/o1-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
-| openai/o3-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
-| openai/o4-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
-| zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
-| google/gemini-2.5-pro | $1.25 | $10.00 | $0.0056 | 1M | reasoning, vision, tools |
-| openai/gpt-5.2 | $1.75 | $14.00 | $0.0079 | 400K | reasoning, vision, agentic, tools |
-| openai/gpt-5.3 | $1.75 | $14.00 | $0.0079 | 128K | reasoning, vision, agentic, tools |
-| openai/gpt-5.3-codex | $1.75 | $14.00 | $0.0079 | 400K | agentic, tools |
-| openai/gpt-4.1 | $2.00 | $8.00 | $0.0050 | 128K | vision, tools |
-| openai/o3 | $2.00 | $8.00 | $0.0050 | 200K | reasoning, tools |
-| google/gemini-3-pro-preview | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
-| google/gemini-3.1-pro | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
-| xai/grok-2-vision | $2.00 | $10.00 | $0.0060 | 131K | vision, tools |
-| openai/gpt-4o | $2.50 | $10.00 | $0.0063 | 128K | vision, agentic, tools |
-| openai/gpt-5.4 | $2.50 | $15.00 | $0.0088 | 400K | reasoning, vision, agentic, tools |
+| Model                       | Input $/M | Output $/M | ~$/request | Context | Features                          |
+| --------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- |
+| anthropic/claude-haiku-4.5  |     $1.00 |      $5.00 |    $0.0030 | 200K    | vision, agentic, tools            |
+| zai/glm-5                   |     $1.00 |      $3.20 |    $0.0021 | 200K    | tools                             |
+| openai/o1-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                  |
+| openai/o3-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                  |
+| openai/o4-mini              |     $1.10 |      $4.40 |    $0.0028 | 128K    | reasoning, tools                  |
+| zai/glm-5-turbo             |     $1.20 |      $4.00 |    $0.0026 | 200K    | tools                             |
+| google/gemini-2.5-pro       |     $1.25 |     $10.00 |    $0.0056 | 1M      | reasoning, vision, tools          |
+| openai/gpt-5.2              |     $1.75 |     $14.00 |    $0.0079 | 400K    | reasoning, vision, agentic, tools |
+| openai/gpt-5.3              |     $1.75 |     $14.00 |    $0.0079 | 128K    | reasoning, vision, agentic, tools |
+| openai/gpt-5.3-codex        |     $1.75 |     $14.00 |    $0.0079 | 400K    | agentic, tools                    |
+| openai/gpt-4.1              |     $2.00 |      $8.00 |    $0.0050 | 128K    | vision, tools                     |
+| openai/o3                   |     $2.00 |      $8.00 |    $0.0050 | 200K    | reasoning, tools                  |
+| google/gemini-3-pro-preview |     $2.00 |     $12.00 |    $0.0070 | 1M      | reasoning, vision, tools          |
+| google/gemini-3.1-pro       |     $2.00 |     $12.00 |    $0.0070 | 1M      | reasoning, vision, tools          |
+| xai/grok-2-vision           |     $2.00 |     $10.00 |    $0.0060 | 131K    | vision, tools                     |
+| openai/gpt-4o               |     $2.50 |     $10.00 |    $0.0063 | 128K    | vision, agentic, tools            |
+| openai/gpt-5.4              |     $2.50 |     $15.00 |    $0.0088 | 400K    | reasoning, vision, agentic, tools |
 
 ### Premium Models ($0.01+/request)
 
-| Model | Input $/M | Output $/M | ~$/request | Context | Features |
-| --- | ---: | ---: | ---: | --- | --- |
-| anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | $0.0090 | 200K | reasoning, vision, agentic, tools |
-| xai/grok-3 | $3.00 | $15.00 | $0.0090 | 131K | reasoning, tools |
-| anthropic/claude-opus-4.6 | $5.00 | $25.00 | $0.0150 | 200K | reasoning, vision, agentic, tools |
-| openai/o1 | $15.00 | $60.00 | $0.0375 | 200K | reasoning, tools |
-| openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools |
-| openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools |
+| Model                       | Input $/M | Output $/M | ~$/request | Context | Features                          |
+| --------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- |
+| anthropic/claude-sonnet-4.6 |     $3.00 |     $15.00 |    $0.0090 | 200K    | reasoning, vision, agentic, tools |
+| xai/grok-3                  |     $3.00 |     $15.00 |    $0.0090 | 131K    | reasoning, tools                  |
+| anthropic/claude-opus-4.6   |     $5.00 |     $25.00 |    $0.0150 | 200K    | reasoning, vision, agentic, tools |
+| openai/o1                   |    $15.00 |     $60.00 |    $0.0375 | 200K    | reasoning, tools                  |
+| openai/gpt-5.2-pro          |    $21.00 |    $168.00 |    $0.0945 | 400K    | reasoning, tools                  |
+| openai/gpt-5.4-pro          |    $30.00 |    $180.00 |    $0.1050 | 400K    | reasoning, tools                  |
 
 > **Free tier:** `nvidia/gpt-oss-120b` costs nothing and serves as automatic fallback when wallet is empty.
 > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.

package/dist/cli.js

@@ -37975,7 +37975,19 @@ function createPayFetchWithPreAuth(baseFetch, client, ttlMs = DEFAULT_TTL_MS, op
   return async (input, init) => {
     const request = new Request(input, init);
     const urlPath = new URL(request.url).pathname;
-    const cached = !options?.skipPreAuth ? cache2.get(urlPath) : void 0;
+    let requestModel = "";
+    if (init?.body) {
+      try {
+        const bodyStr = init.body instanceof Uint8Array ? new TextDecoder().decode(init.body) : typeof init.body === "string" ? init.body : "";
+        if (bodyStr) {
+          const parsed = JSON.parse(bodyStr);
+          requestModel = parsed.model ?? "";
+        }
+      } catch {
+      }
+    }
+    const cacheKey2 = `${urlPath}:${requestModel}`;
+    const cached = !options?.skipPreAuth ? cache2.get(cacheKey2) : void 0;
     if (cached && Date.now() - cached.cachedAt < ttlMs) {
       try {
         const payload2 = await client.createPaymentPayload(cached.paymentRequired);
@@ -37988,9 +38000,9 @@ function createPayFetchWithPreAuth(baseFetch, client, ttlMs = DEFAULT_TTL_MS, op
         if (response2.status !== 402) {
           return response2;
         }
-        cache2.delete(urlPath);
+        cache2.delete(cacheKey2);
       } catch {
-        cache2.delete(urlPath);
+        cache2.delete(cacheKey2);
       }
     }
     const clonedRequest = request.clone();
@@ -38013,7 +38025,7 @@ function createPayFetchWithPreAuth(baseFetch, client, ttlMs = DEFAULT_TTL_MS, op
       } catch {
       }
       paymentRequired = httpClient.getPaymentRequiredResponse(getHeader, body);
-      cache2.set(urlPath, { paymentRequired, cachedAt: Date.now() });
+      cache2.set(cacheKey2, { paymentRequired, cachedAt: Date.now() });
     } catch (error) {
       throw new Error(
         `Failed to parse payment requirements: ${error instanceof Error ? error.message : "Unknown error"}`,
@@ -46367,12 +46379,7 @@ async function checkForUpdates() {
 import { readFileSync, writeFileSync, mkdirSync } from "fs";
 import { join as join7, dirname as dirname2 } from "path";
 import { homedir as homedir4 } from "os";
-var DEFAULT_FILE_PATH = join7(
-  homedir4(),
-  ".openclaw",
-  "blockrun",
-  "exclude-models.json"
-);
+var DEFAULT_FILE_PATH = join7(homedir4(), ".openclaw", "blockrun", "exclude-models.json");
 function loadExcludeList(filePath = DEFAULT_FILE_PATH) {
   try {
     const raw = readFileSync(filePath, "utf-8");
@@ -46752,8 +46759,7 @@ function categorizeError(status, body) {
   if (status === 401) return "auth_failure";
   if (status === 402) return "payment_error";
   if (status === 403) {
-    if (/plan.*limit|quota.*exceeded|subscription|allowance/i.test(body))
-      return "quota_exceeded";
+    if (/plan.*limit|quota.*exceeded|subscription|allowance/i.test(body)) return "quota_exceeded";
     return "auth_failure";
   }
   if (status === 429) return "rate_limited";
@@ -49040,6 +49046,7 @@ data: [DONE]
     let upstream;
     let lastError;
     let actualModelUsed = modelId;
+    const failedAttempts = [];
     for (let i = 0; i < modelsToTry.length; i++) {
       const tryModel = modelsToTry[i];
       const isLastAttempt = i === modelsToTry.length - 1;
@@ -49088,6 +49095,11 @@ data: [DONE]
         body: result.errorBody || "Unknown error",
         status: result.errorStatus || 500
       };
+      failedAttempts.push({
+        model: tryModel,
+        reason: result.errorCategory || `HTTP ${result.errorStatus || 500}`,
+        status: result.errorStatus || 500
+      });
       if (result.isProviderError && !isLastAttempt) {
         const isExplicitModelError = !routingDecision;
         const isUnknownExplicitModel = isExplicitModelError && /unknown.*model|invalid.*model/i.test(result.errorBody || "");
@@ -49225,7 +49237,10 @@ data: [DONE]
       }
     }
     if (!upstream) {
-      const rawErrBody = lastError?.body || "All models in fallback chain failed";
+      const attemptSummary = failedAttempts.length > 0 ? failedAttempts.map((a) => `${a.model} (${a.reason})`).join(", ") : "unknown";
+      const structuredMessage = failedAttempts.length > 0 ? `All ${failedAttempts.length} models failed. Tried: ${attemptSummary}` : "All models in fallback chain failed";
+      console.log(`[ClawRouter] ${structuredMessage}`);
+      const rawErrBody = lastError?.body || structuredMessage;
       const errStatus = lastError?.status || 502;
       const transformedErr = transformPaymentError(rawErrBody);
       if (headersSentEarly) {
@@ -49284,7 +49299,7 @@ data: [DONE]
             id: rsp.id ?? `chatcmpl-${Date.now()}`,
             object: "chat.completion.chunk",
             created: rsp.created ?? Math.floor(Date.now() / 1e3),
-            model: rsp.model ?? "unknown",
+            model: actualModelUsed || rsp.model || "unknown",
             system_fingerprint: null
           };
           if (rsp.choices && Array.isArray(rsp.choices)) {
@@ -49399,6 +49414,13 @@ data: [DONE]
           responseChunks.push(Buffer.from(sseData));
         }
       }
+      if (routingDecision) {
+        const costComment = `: cost=$${routingDecision.costEstimate.toFixed(4)} savings=${(routingDecision.savings * 100).toFixed(0)}% model=${actualModelUsed} tier=${routingDecision.tier}
+
+`;
+        safeWrite(res, costComment);
+        responseChunks.push(Buffer.from(costComment));
+      }
       safeWrite(res, "data: [DONE]\n\n");
       responseChunks.push(Buffer.from("data: [DONE]\n\n"));
       res.end();
@@ -49427,6 +49449,10 @@ data: [DONE]
           responseHeaders["x-clawrouter-agentic-score"] = routingDecision.agenticScore.toFixed(2);
         }
       }
+      if (routingDecision) {
+        responseHeaders["x-clawrouter-cost"] = routingDecision.costEstimate.toFixed(6);
+        responseHeaders["x-clawrouter-savings"] = `${(routingDecision.savings * 100).toFixed(0)}%`;
+      }
       const bodyParts = [];
       if (upstream.body) {
         const chunks = await readBodyWithTimeout(upstream.body);
@@ -49457,6 +49483,16 @@ data: [DONE]
         }
         budgetDowngradeNotice = void 0;
       }
+      if (actualModelUsed && responseBody.length > 0) {
+        try {
+          const parsed = JSON.parse(responseBody.toString());
+          if (parsed.model !== void 0) {
+            parsed.model = actualModelUsed;
+            responseBody = Buffer.from(JSON.stringify(parsed));
+          }
+        } catch {
+        }
+      }
       if (budgetDowngradeHeaderMode) {
         responseHeaders["x-clawrouter-budget-downgrade"] = "1";
         responseHeaders["x-clawrouter-budget-mode"] = budgetDowngradeHeaderMode;