Update token addresses parsing + add Jupiter parser testing with a real route fixture #88

hassan-anchor · 2025-11-06T18:56:48Z

This PR adds a real Jupiter route fixture and tests our parser against the expected fields from the fixture. This establishes the testing pattern for validating instruction parsers against real on-chain transactions.

We've also currently removed input_token_address from the parser so that we don't continue showing incorrect input token address. It's being fixed in #89. The account index for output token address has also been updated to reflect the destination mint correctly

Copilot

Pull Request Overview

This PR adds a new test fixture file for Jupiter Route swap transactions on Solana. The fixture captures a real mainnet transaction (WSOL to USDT swap) to be used for testing the Jupiter swap parser implementation.

Adds comprehensive test data including instruction details, account metadata, and expected parsed fields
Documents a 6-instruction transaction with focus on instruction #4 (the actual swap)
Includes 25 account entries with role descriptions and expected output fields for validation

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2025-11-06T19:02:13Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+    "program_id": "JUP6LkbZbjS1jKKwapdHNy74zcZ3tLUZoi5QNyVTaV4",
+    "input_amount": "1704961004145737728",
+    "quoted_output_amount": "54975581388800",
+    "input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",


The input_token_address appears to be incorrect. It's set to "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA" which is the SPL Token Program ID, not a token mint address. According to the transaction description (line 2), this is a "WSOL to USDT swap", so the input token address should be the Wrapped SOL mint address "So11111111111111111111111111111111111111112" (which appears at line 102).

Suggested change

"input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",

"input_token_address": "So11111111111111111111111111111111111111112",

this looks right

Copilot · 2025-11-06T19:02:14Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+    "input_amount": "1704961004145737728",
+    "quoted_output_amount": "54975581388800",
+    "input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",
+    "output_token_address": "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA",


The output_token_address appears to be incorrect. It's set to "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA" which is described as "User wallet" (line 21), not a token mint address. According to the transaction description (line 2), this is a "WSOL to USDT swap", so the output token address should be the USDT mint address. Please verify and use the correct USDT mint address (typically "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB" on mainnet).

Suggested change

"output_token_address": "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA",

"output_token_address": "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB",

should be Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk

{5 items amm: "whirLbMiicVdio4qvUfM5KAg6Ct8VwpYzGff3uctyCc" inputMint: "So11111111111111111111111111111111111111112" inputAmount: "2000000" outputMint: "Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk" outputAmount: "1550653" }

Copilot · 2025-11-06T19:02:14Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+      "pubkey": "CCifuNxNLBZV9ch94GQ4QgdrmbBdG13xDfReomzqvhMC",
+      "signer": false,
+      "writable": false,
+      "description": "Account 14"
+    },
+    {
+      "pubkey": "So11111111111111111111111111111111111111112",
+      "signer": false,
+      "writable": false,
+      "description": "Wrapped SOL"
+    },
+    {
+      "pubkey": "Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk",
+      "signer": false,
+      "writable": false,
+      "description": "Jupiter authority"
+    },
+    {
+      "pubkey": "3c5JEJ3un3HZAtWvZ77nhNGxDGqmWM7uZ1cx4bGDsKE8",
+      "signer": false,
+      "writable": false,
+      "description": "User source token account"
+    },
+    {
+      "pubkey": "4iBF54K8AY5dbwFZL8JBktqDrRvAnEkBs42aSRDYB14p",
+      "signer": false,
+      "writable": false,
+      "description": "Account 18"
+    },
+    {
+      "pubkey": "FAXnNWMXbadmfMTfWtEu3WDymtRwsxYLGdbKoJbfLKsK",
+      "signer": false,
+      "writable": false,
+      "description": "User destination token account"
+    },
+    {
+      "pubkey": "3YYrbiosq79pthXhFV8MwXThXWgb4Wn85fMiqPoo8dq4",
+      "signer": false,
+      "writable": false,
+      "description": "Account 20"
+    },
+    {
+      "pubkey": "FdV51SZanY1thtYtseN5enYiASp78r7gtEcTo3xxg1eS",
+      "signer": false,
+      "writable": false,
+      "description": "Account 21"
+    },
+    {
+      "pubkey": "4ThAi4HvBnXpgjBs5BDUQHosHjqMc1G6b9L88Djq1Ue8",
+      "signer": false,
+      "writable": false,
+      "description": "Account 22"
+    },
+    {
+      "pubkey": "EHmLbEKVdix9brJJ13ey5o3VHo2f8w8Rr5NEwhBtHrrT",
+      "signer": false,
+      "writable": false,
+      "description": "Account 23"
+    },
+    {
+      "pubkey": "68sWwn3c2exPMnAGe2STD3LFAc97bVBvGaGCHSEctK1",
+      "signer": false,
+      "writable": false,
+      "description": "Account 24"
+    }


The descriptions for these accounts are too generic ("Account 14", "Account 18", "Account 20", "Account 21", "Account 22", "Account 23", "Account 24"). For a test fixture, these should have meaningful descriptions that explain the role of each account in the Jupiter swap transaction. This will make the test more maintainable and help developers understand the expected transaction structure.

prasanna-anchorage

I don't know why copilot thinks this is WSOL-> USDT when the explorer shows WSOL to USELESS AFAICT

prasanna-anchorage · 2025-11-06T19:21:53Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+    "input_amount": "1704961004145737728",
+    "quoted_output_amount": "54975581388800",
+    "input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",
+    "output_token_address": "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA",


this doesn't look right since this is also the address for the signer.

Output token is actually Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk

@prasanna-anchorage Should this be the source of truth in expected fields?

"input_token_address": "So11111111111111111111111111111111111111112", "output_token_address": "Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk"

Yeah, we might need to eventually go deeper and expose the routing but we cant really know that at this stage (I doubt simulation can either)

Currently, the parser is getting these addresses from the top two of the account list. What was the logic behind doing that? Is there a way to get the token addresses from the accounts list?

prasanna-anchorage · 2025-11-06T19:25:56Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+    "input_amount": "1704961004145737728",
+    "quoted_output_amount": "54975581388800",
+    "input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",
+    "output_token_address": "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA",


should be Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk

{5 items amm: "whirLbMiicVdio4qvUfM5KAg6Ct8VwpYzGff3uctyCc" inputMint: "So11111111111111111111111111111111111111112" inputAmount: "2000000" outputMint: "Dz9mQ9NzkBcCsuGPFJ3r1bS4wgqKMHBPiVuniW8Mbonk" outputAmount: "1550653" }

prasanna-anchorage · 2025-11-06T19:26:04Z

src/chain_parsers/visualsign-solana/tests/fixtures/jupiter_swap/sample_route.json

+    "program_id": "JUP6LkbZbjS1jKKwapdHNy74zcZ3tLUZoi5QNyVTaV4",
+    "input_amount": "1704961004145737728",
+    "quoted_output_amount": "54975581388800",
+    "input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",


this looks right

prasanna-anchorage · 2025-11-07T18:59:58Z

src/chain_parsers/visualsign-solana/src/presets/jupiter_swap/mod.rs


    let in_token = accounts.first().map(|addr| get_token_info(addr, in_amount));
-    let out_token = accounts.get(1).map(|addr| get_token_info(addr, out_amount));
+    let out_token = accounts.get(5).map(|addr| get_token_info(addr, out_amount));


this needs a comment that this is hardcoded to 5

prasanna-anchorage · 2025-11-07T19:00:38Z

src/chain_parsers/visualsign-solana/src/presets/jupiter_swap/mod.rs

            platform_fee_field.is_some(),
            "Should have Platform Fee field when platform_fee_bps > 0"
        );
        println!("✅ Platform Fee field present in expanded fields");


I'm okay with these emojis in tests but we should avoid println! in non test code

this is an exisitng test

All the println! in mod.rs are in tests

ok, great, I was just looking at the small diff

prasanna-anchorage · 2025-11-07T19:01:04Z

src/chain_parsers/visualsign-solana/src/presets/jupiter_swap/mod.rs

        );
        println!("✅ Platform Fee field present in expanded fields");
    }
+    mod fixture_test;


why is this here?

I saw this comment of yours in the template file.

// To add these tests to the existing tests module in mod.rs, add this line at the end // of the existing `mod tests` block (before the closing brace): // // mod fixture_tests; // // This file will then be compiled as `tests::fixture_tests`

If I remove this, the test doesn't get included in the suite

ok, you want to put them at the top of the file or in the mod.rs

set fixture

a9dc4dc

Copilot AI review requested due to automatic review settings November 6, 2025 18:56

add tests

481169a

Copilot AI reviewed Nov 6, 2025

View reviewed changes

prasanna-anchorage requested changes Nov 6, 2025

View reviewed changes

hassan-anchor added 8 commits November 6, 2025 19:41

linter

0f56f43

rename file

ba3fa77

fix amount in expected fields

f162a3d

linter

cd0075f

revert rename

9c2e178

more lint

98c2dd2

fix fixture

a757358

remove input_token_address + fix output_token index

dd492ff

hassan-anchor changed the title ~~Add Jupiter parser testing with a real route fixture~~ Update token addresses parsing + add Jupiter parser testing with a real route fixture Nov 7, 2025

hassan-anchor requested a review from prasanna-anchorage November 7, 2025 18:46

prasanna-anchorage approved these changes Nov 7, 2025

View reviewed changes

hassan-anchor merged commit 214ae59 into main Nov 7, 2025
4 checks passed

hassan-anchor deleted the muhammad/jupiter-real-route-test branch November 7, 2025 20:05

	"input_token_address": "TokenkegQfeZyiNwAJbNbGKPFXCWuBvf9Ss623VQ5DA",
	"input_token_address": "So11111111111111111111111111111111111111112",

	"output_token_address": "B7hSadyLX8YhNT8RDcK8RbnR3KAfX4HbWvV89XmeqitA",
	"output_token_address": "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB",

Update token addresses parsing + add Jupiter parser testing with a real route fixture #88

Update token addresses parsing + add Jupiter parser testing with a real route fixture #88

Uh oh!

Conversation

hassan-anchor commented Nov 6, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Uh oh!

Copilot AI Nov 6, 2025

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 6, 2025

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI Nov 6, 2025

Choose a reason for hiding this comment

Uh oh!

prasanna-anchorage left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

hassan-anchor Nov 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

hassan-anchor Nov 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

hassan-anchor commented Nov 6, 2025 •

edited

Loading

hassan-anchor Nov 7, 2025 •

edited

Loading

hassan-anchor Nov 7, 2025 •

edited

Loading