🌐 Web query:

Mino API SSE COMPLETE event stream closure documentation

💡 Result:

In Mino’s POST /v1/automation/run-sse SSE response, the COMPLETE event is the terminal “automation finished” event (success or failure) and contains the final status/result payload. After you receive type: "COMPLETE", you should treat the stream as finished and stop reading/close your SSE client. [1][2]

• Mino documents the SSE event types and explicitly defines COMPLETE = “Automation finished (success or failure)”. [2]
• The endpoint’s example stream shows STARTED → STREAMING_URL (optional) → PROGRESS → COMPLETE (final). [1]
• If you’re using the browser EventSource API, the client-side way to terminate the connection is eventSource.close() once you detect completion. [3]

Sources:
[1] https://tinyfish.mintlify.app/api-reference/automation/run-browser-automation-with-sse-streaming
[2] https://docs.mino.ai/quick-start
[3] https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events

🏁 Script executed:

# First, let's look at the full context of the file to understand stream setup
find . -type f -name "route.ts" | grep -i "compare-cards"

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 123

🏁 Script executed:

# Search for where reader is created and how the response is handled
fd "compare-cards" --type f -e ts -e tsx

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 55

🏁 Script executed:

cat -n ./credit-aggregator/app/api/compare-cards/route.ts | sed -n '180,260p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 3296

🏁 Script executed:

# Look for the complete function that creates the reader
cat -n ./credit-aggregator/app/api/compare-cards/route.ts | sed -n '150,200p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1683

🏁 Script executed:

# Check if there's any try-finally or cleanup logic around the streaming section
rg -A 50 "TextDecoder" ./credit-aggregator/app/api/compare-cards/route.ts

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1963

🏁 Script executed:

# Check for try-finally or cleanup logic around the entire reader section
cat -n ./credit-aggregator/app/api/compare-cards/route.ts | sed -n '140,280p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 5339

🏁 Script executed:

# Check the broader context to see if there's any finally block or cleanup
wc -l ./credit-aggregator/app/api/compare-cards/route.ts

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 127

🏁 Script executed:

# Get the complete function to understand error handling scope
cat -n ./credit-aggregator/app/api/compare-cards/route.ts

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 17446

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

             } else if (event.type === "step") {
               // Legacy step event - ignore
             } else if (event.type === "complete") {
-              setResults(event.cards || []);
+              // Only set results if no cards were accumulated from site_complete events
+              if (event.cards && event.cards.length > 0) {
+                setResults((prev) => prev.length === 0 ? event.cards : prev);
+              }
               setLoading(false);
             } else if (event.type === "error") {

Alternatively, if complete is only sent without per-site cards, keep it as-is but document the expected server behavior.

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

🏁 Script executed:

# Find the button.tsx file
find . -name "button.tsx" -o -name "button.ts" | head -20

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 117

🏁 Script executed:

# Also search for the file in the credit-aggregator directory structure
fd -t f "button.tsx" credit-aggregator/

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 115

🏁 Script executed:

cat -n credit-aggregator/components/ui/button.tsx

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 2724

🏁 Script executed:

# Search for Button usage in form contexts
rg -n --type=tsx -B2 -A2 '<Button' credit-aggregator/ | head -100

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 100

🏁 Script executed:

# Search for Button usage patterns
rg -n '<Button' credit-aggregator/ --no-type-list -A2 -B2 | head -150

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 516

🏁 Script executed:

# Search for Button usage patterns in the codebase
rg '<Button' credit-aggregator/ -A2 -B2 | head -200

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 415

🏁 Script executed:

# Search for all Button component usages
rg 'Button' credit-aggregator/ -A5 | grep -E '(<Button|type=)' | head -100

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 182

🏁 Script executed:

# More targeted search for Button usages and check if type is specified
rg '<Button' credit-aggregator/ -A10 | grep -v '^--$' | head -150

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 797

🏁 Script executed:

# First, locate and read the stepper.tsx file
find . -name "stepper.tsx" -type f | head -5

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 118

🏁 Script executed:

# Get file size and read the specific lines mentioned
cat -n credit-aggregator/components/ui/stepper.tsx | sed -n '130,170p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1375

🏁 Script executed:

# Search for StepperTrigger usages in the codebase
rg -n --type=tsx 'StepperTrigger' -C2

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 100

🏁 Script executed:

# Search for StepperTrigger usages without tsx filter
rg -n 'StepperTrigger' -C2

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1483

🏁 Script executed:

# Check package.json for `@radix-ui/react-slot` dependency
cat package.json | grep -A20 '"dependencies"' | head -30

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 117

🏁 Script executed:

# Find package.json in the repo
find . -name "package.json" -type f

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 128

🏁 Script executed:

# Check the repo root structure
ls -la | head -20

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 988

🏁 Script executed:

# Search for any files that import from stepper.tsx
rg -n "from.*stepper" -i

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 55

🏁 Script executed:

# Check credit-aggregator package.json for dependencies
cat credit-aggregator/package.json | grep -E '("dependencies"|"@radix-ui")' -A30

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 656

🏁 Script executed:

# Search for StepperTrigger usage specifically in credit-aggregator
rg -n 'StepperTrigger' credit-aggregator/ -C3

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1875

🏁 Script executed:

# Search for actual usage of Stepper component in pages or app
find credit-aggregator -type f \( -name "*.tsx" -o -name "*.ts" \) -exec grep -l "Stepper" {} \; | grep -v "stepper.tsx"

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 55

🏁 Script executed:

# Look for actual StepperTrigger usage in context
rg -n '<Stepper' credit-aggregator/ -A5 -B5

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 1659

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

🏁 Script executed:

cat -n credit-aggregator/lib/mino-client.ts | sed -n '1,150p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 5016

🏁 Script executed:

cat -n credit-aggregator/lib/mino-client.ts | sed -n '48,142p'

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 3179

🏁 Script executed:

# Let me verify the ReadableStreamDefaultReader API and check if there are any other early return paths
cat -n credit-aggregator/lib/mino-client.ts | sed -n '34,142p' | grep -n "return"

Repository: tinyfish-io/TinyFish-cookbook

Length of output: 180

🌐 Web query:

ReadableStreamDefaultReader cancel() method JavaScript Node.js resource cleanup

💡 Result:

In Node.js (Web Streams API), ReadableStreamDefaultReader.prototype.cancel(reason) is the consumer-side way to say “I’m done—stop producing data and clean up.”

What it does:

• Signals loss of interest and cancels the stream, even if chunks are still queued; any unread queued data is discarded and the stream won’t be readable afterward. [1]
• Runs underlying-source cleanup: the reason is forwarded to the stream’s underlying source cancel() algorithm (if provided), which is where you should stop I/O, clear timers, close file handles/sockets, etc. [2]
• If you already hold the reader lock, reader.cancel() is effectively the same as canceling the associated stream. [1]

How this relates to resource cleanup in Node:

• If your stream is backed by something expensive (network/file/timers), implement the underlying source’s cancel(reason) so it actually frees those resources. reader.cancel() is the trigger that calls into that cleanup path. [2]

Practical pattern (early-exit cleanup):

const reader = stream.getReader();
try {
  while (true) {
    const { value, done } = await reader.read();
    if (done) break;
    if (shouldStop(value)) {
      await reader.cancel("no longer needed"); // triggers underlying cleanup
      break;
    }
  }
} finally {
  // Optional: if you intend to hand the stream to someone else instead of canceling it,
  // release the lock (this does NOT cancel).
  // reader.releaseLock();
}

If you don’t want to discard unread queued chunks and you want another consumer to keep reading later, use releaseLock() instead of cancel() (it releases the lock and leaves queued chunks available). [3]

Sources: MDN ReadableStreamDefaultReader.cancel() [1], WHATWG Streams spec (cancel forwards reason to underlying source cancel) [2], MDN releaseLock() [3].

[1] https://developer.mozilla.org/en-US/docs/Web/API/ReadableStreamDefaultReader/cancel
[2] https://streams.spec.whatwg.org/
[3] https://developer.mozilla.org/en-US/docs/Web/API/ReadableStreamDefaultReader/releaseLock

🌐 Web query:

Mino API run-sse COMPLETE event documentation stream close

💡 Result:

For Mino’s POST /v1/automation/run-sse, the response is a Server-Sent Events stream (text/event-stream) that emits these message types: STARTED, optional STREAMING_URL, PROGRESS, COMPLETE, plus periodic HEARTBEAT keep-alives. COMPLETE includes the final status (e.g., COMPLETED) and resultJson payload. [1]

How to close the stream: Mino does not document a separate “close” event—treat type: "COMPLETE" as the terminal message (no more meaningful events are expected after it). On the client side, close your SSE connection immediately when you receive COMPLETE (e.g., eventSource.close() or abort your streaming HTTP request). [1]

Source

1. Mino docs: “Run browser automation with SSE streaming” (/v1/automation/run-sse). [1]

         if (isCompleteEvent(event)) {
           if (verbose) {
             console.log("[SUCCESS] Automation completed");
           }
+          await reader.cancel();
           return {
             success: true,
             result: event.resultJson,
             streamingUrl,
             events,
           };
         }
 
         // Check for errors
         if (isErrorEvent(event)) {
           const errorMsg = event.message || "Automation failed";
           if (verbose) {
             console.error(`[ERROR] ${errorMsg}`);
           }
+          await reader.cancel();
           return {
             success: false,
             error: errorMsg,
             streamingUrl,
             events,
           };
         }

Note: Consider also adding await reader.cancel() before the return at line 125 and wrapping the reader section in try-finally to handle the catch block scenario at line 131.

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.