search

zeta-chain / protocol-contracts

Protocol contracts implementing the core logic of the protocol, deployed on ZetaChain and on connected chains
MIT License
70 stars 58 forks source link

feat: prototype localnet #202

Closed skosito closed 4 months ago

skosito commented 4 months ago

start local hardhat node and worker which deploys evm/zevm contracts and listen to Call/WithdrawAndCall/Deposit events

yarn localnet

also, adding 4 hardhat tasks to interact with localnet (we can add more in follow up PRs if needed):

npx hardhat zevm-call --network localhost
npx hardhat zevm-withdraw-and-call --network localhost
npx hardhat evm-call --network localhost
npx hardhat evm-deposit-and-call --network localhost

Summary by CodeRabbit

coderabbitai[bot] commented 4 months ago

Walkthrough

The changes involve refactoring Sender to SenderZEVM in the ZEVM contract to create consistency with the ZEVM environment, adding new tasks in localnet.ts for interacting with EVM and ZEVM contracts, and introducing a worker script (worker.ts) to deploy and interact across environments. A new scripts/readme.md file documents the worker script functionalities.

Changes

File(s) Change Summary
pkg/contracts/.../senderzevm.go Refactor: Renamed entities related to Sender contract to SenderZEVM for consistent naming.
tasks/localnet.ts New Tasks: Added tasks for calling contracts and managing assets between ZEVM and EVM environments.
scripts/worker.ts New Script: Introduced worker script for deployment and interaction across EVM and ZEVM contracts.
scripts/readme.md Documentation: Added documentation for the worker script, outlining its purpose and usage.

Sequence Diagram(s)

sequenceDiagram
    participant Worker as worker.ts
    participant EVM as EVM
    participant ZEVM as ZEVM
    participant GatewayEVM as GatewayEVM
    participant GatewayZEVM as GatewayZEVM

    Worker->>EVM: Deploy ReceiverEVM Contract
    Worker->>ZEVM: Deploy SenderZEVM Contract

    loop Management
        note over Worker: Mint and Transfer Tokens
        Worker->>EVM: Mint ERC-20
        Worker->>ZEVM: Mint ZRC-20
    end

    loop Interactions
        note over Worker: Calls, Withdrawals, Deposits through Gateways
        Worker->>GatewayZEVM: Call ReceiverEVM
        GatewayZEVM->>EVM: Execute Call
        Worker->>GatewayEVM: Call SenderZEVM
        GatewayEVM->>ZEVM: Execute Call
    end

Poem

In a world of EVM and ZEVM blend,
We renamed contracts to better portend.
Tasks now call, withdraw, and send,
Local nets and workers, they extend.
With code aligned from start to end,
Deployments easier, changes mend.
🐇✨

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share - [X](https://twitter.com/intent/tweet?text=I%20just%20used%20%40coderabbitai%20for%20my%20code%20review%2C%20and%20it%27s%20fantastic%21%20It%27s%20free%20for%20OSS%20and%20offers%20a%20free%20trial%20for%20the%20proprietary%20code.%20Check%20it%20out%3A&url=https%3A//coderabbit.ai) - [Mastodon](https://mastodon.social/share?text=I%20just%20used%20%40coderabbitai%20for%20my%20code%20review%2C%20and%20it%27s%20fantastic%21%20It%27s%20free%20for%20OSS%20and%20offers%20a%20free%20trial%20for%20the%20proprietary%20code.%20Check%20it%20out%3A%20https%3A%2F%2Fcoderabbit.ai) - [Reddit](https://www.reddit.com/submit?title=Great%20tool%20for%20code%20review%20-%20CodeRabbit&text=I%20just%20used%20CodeRabbit%20for%20my%20code%20review%2C%20and%20it%27s%20fantastic%21%20It%27s%20free%20for%20OSS%20and%20offers%20a%20free%20trial%20for%20proprietary%20code.%20Check%20it%20out%3A%20https%3A//coderabbit.ai) - [LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fcoderabbit.ai&mini=true&title=Great%20tool%20for%20code%20review%20-%20CodeRabbit&summary=I%20just%20used%20CodeRabbit%20for%20my%20code%20review%2C%20and%20it%27s%20fantastic%21%20It%27s%20free%20for%20OSS%20and%20offers%20a%20free%20trial%20for%20proprietary%20code)
Tips ### Chat There are 3 ways to chat with [CodeRabbit](https://coderabbit.ai): - Review comments: Directly reply to a review comment made by CodeRabbit. Example: - `I pushed a fix in commit .` - `Generate unit testing code for this file.` - `Open a follow-up GitHub issue for this discussion.` - Files and specific lines of code (under the "Files changed" tab): Tag `@coderabbitai` in a new review comment at the desired location with your query. Examples: - `@coderabbitai generate unit testing code for this file.` - `@coderabbitai modularize this function.` - PR comments: Tag `@coderabbitai` in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples: - `@coderabbitai generate interesting stats about this repository and render them as a table.` - `@coderabbitai show all the console.log statements in this repository.` - `@coderabbitai read src/utils.ts and generate unit testing code.` - `@coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.` - `@coderabbitai help me debug CodeRabbit configuration file.` Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. ### CodeRabbit Commands (invoked as PR comments) - `@coderabbitai pause` to pause the reviews on a PR. - `@coderabbitai resume` to resume the paused reviews. - `@coderabbitai review` to trigger an incremental review. This is useful when automatic reviews are disabled for the repository. - `@coderabbitai full review` to do a full review from scratch and review all the files again. - `@coderabbitai summary` to regenerate the summary of the PR. - `@coderabbitai resolve` resolve all the CodeRabbit review comments. - `@coderabbitai configuration` to show the current CodeRabbit configuration for the repository. - `@coderabbitai help` to get help. Additionally, you can add `@coderabbitai ignore` anywhere in the PR description to prevent this PR from being reviewed. ### CodeRabbit Configration File (`.coderabbit.yaml`) - You can programmatically configure CodeRabbit by adding a `.coderabbit.yaml` file to the root of your repository. - Please see the [configuration documentation](https://docs.coderabbit.ai/guides/configure-coderabbit) for more information. - If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: `# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json` ### Documentation and Community - Visit our [Documentation](https://coderabbit.ai/docs) for detailed information on how to use CodeRabbit. - Join our [Discord Community](https://discord.com/invite/GsXnASn26c) to get help, request features, and share feedback. - Follow us on [X/Twitter](https://twitter.com/coderabbitai) for updates and announcements.
codecov-commenter commented 4 months ago

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 59.25%. Comparing base (6bf41ee) to head (be1f176).

Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #202 +/- ## ======================================= Coverage 59.25% 59.25% ======================================= Files 31 31 Lines 1048 1048 Branches 262 217 -45 ======================================= Hits 621 621 Misses 427 427 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

lumtis commented 4 months ago

start localnet (these 2 commands in 2 separate terminals so you can follow logs) yarn localnode yarn localnet

What is exactly localnet if localnode represent the Hardhat node? Couldn't we think about merging both?

skosito commented 4 months ago

start localnet (these 2 commands in 2 separate terminals so you can follow logs) yarn localnode yarn localnet

What is exactly localnet if localnode represent the Hardhat node? Couldn't we think about merging both?

good point, localnet is not good name, it is deploying contracts on localnode and listening to events and calling contracts, so maybe it should be called worker instead of localnet

i dont think we should merge these 2, its better to run separately and see logs of both

fadeev commented 4 months ago

Do I understand correctly that this essentially deploys protocol contracts to a chain running locally managed by Hardhat. Then it monitors existing connected blockchains like Sepolia for incoming transactions (acting sort of like zetaclient, but without voting and consensus) and processes these calls by calling universal apps on this chain that's running in Hardhat.

skosito commented 4 months ago

Do I understand correctly that this essentially deploys protocol contracts to a chain running locally managed by Hardhat. Then it monitors existing connected blockchains like Sepolia for incoming transactions (acting sort of like zetaclient, but without voting and consensus) and processes these calls by calling universal apps on this chain that's running in Hardhat.

yes, but currently there is no external blockchain to be monitored, but hardhat local node is playing the role of both evm and zevm, and worker is basically simplified zetaclient

skosito commented 4 months ago

@coderabbitai review

coderabbitai[bot] commented 4 months ago
Actions performed Review triggered. > Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.
skosito commented 4 months ago

@coderabbitai review

coderabbitai[bot] commented 4 months ago
Actions performed Review triggered. > Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.
skosito commented 4 months ago

@coderabbitai how are these files ignored:

scripts/worker.ts is excluded by none and included by none
tasks/localnet.ts is excluded by none and included by none

they are included in config:

reviews:
  path_filters:
    - "pkg/**"
    - "typechain-types/**"
    - "docs/**"
    - "data/**"
  path_instructions:
    - path: 'contracts/**'
      instructions: >-
        Review the Solidity contracts for security vulnerabilities and best practices.
    - path: 'test/**'
      instructions: >-
        Review the test files for proper coverage, edge cases, and best practices.
    - path: 'scripts/**'
      instructions: >-
        Review the scripts for best practices.
    - path: 'tasks/**'
      instructions: >-
        Review the tasks for best practices.
  auto_review:
    base_branches:
      - main
coderabbitai[bot] commented 4 months ago

[!TIP] For best results, initiate chat on the files or code changes.

The list of workflows did not include "CodeRabbit Review". The correct workflow name needs to be identified. Here are the workflows available:

Since there is no workflow named "CodeRabbit Review", it might be possible that the workflow related to the review process is named differently or not present.

@skosito, it appears that there is no workflow named "CodeRabbit Review" in the repository. Could you please confirm the exact name of the workflow that handles the review process? This will help in accurately retrieving the configuration settings and resolving the issue with ignored files.

Analysis chain --- --- --- --- --- --- --- ---
Scripts executed The following scripts were executed for the analysis: Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name == "CodeRabbit Review") | .id' | xargs -I{} gh api repos/zeta-chain/protocol-contracts/actions/workflows/{}/runs --jq '.workflow_runs[0].id' | xargs -I{} gh api repos/zeta-chain/protocol-contracts/actions/runs/{}/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | xargs curl -s ``` Length of output: 643 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name == "CodeRabbit Review") | .id') run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id') log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url') curl -s $log_url ``` Length of output: 880 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name == "CodeRabbit Review") | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 919 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name | contains("CodeRabbit")) | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 921 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name | test("CodeRabbit"; "i")) | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 922 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # Dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name | contains("CodeRabbit")) | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 921 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # List all workflows to identify the correct workflow name. gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[].name' # Assuming the correct workflow name is identified, dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name == "CodeRabbit Review") | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 1096 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # List all workflows to identify the correct workflow name. gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[].name' # Assuming the correct workflow name is identified, dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name | contains("Review")) | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 1094 --- Script: ```shell #!/bin/bash # Check if the files exist in the repository. fd 'worker.ts' --search-path='scripts' --exact-depth=1 fd 'localnet.ts' --search-path='tasks' --exact-depth=1 # List all workflows to identify the correct workflow name. gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | {name: .name, id: .id}' # Assuming the correct workflow name is identified, dump the current configuration settings to verify path filters and instructions. workflow_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows --jq '.workflows[] | select(.name | contains("Review")) | .id' | head -n 1) run_id=$(gh api repos/zeta-chain/protocol-contracts/actions/workflows/$workflow_id/runs --jq '.workflow_runs[0].id' | head -n 1) log_url=$(gh api repos/zeta-chain/protocol-contracts/actions/runs/$run_id/jobs --jq '.jobs[0].steps[] | select(.name == "Dump Configuration") | .log_url' | head -n 1) curl -s $log_url ``` Length of output: 1316
skosito commented 4 months ago

@coderabbitai full review

coderabbitai[bot] commented 4 months ago
Actions performed Full review triggered.
skosito commented 4 months ago

@coderabbitai full review

coderabbitai[bot] commented 4 months ago
Actions performed Full review triggered.
skosito commented 4 months ago

@coderabbitai full review

coderabbitai[bot] commented 4 months ago
Actions performed Full review triggered.
skosito commented 4 months ago

@coderabbitai full review

coderabbitai[bot] commented 4 months ago
Actions performed Full review triggered.
lumtis commented 4 months ago

I get this error when starting localnet:

[NODE] <--- JS stacktrace --->
[NODE]
[NODE] FATAL ERROR: Reached heap limit Allocation failed - JavaScript heap out of memory
[NODE]  1: 0x1026f2984 node::Abort() [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  2: 0x1026f2b74 node::ModifyCodeGenerationFromStrings(v8::Local<v8::Context>, v8::Local<v8::Value>, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  3: 0x1028356e8 v8::Utils::ReportOOMFailure(v8::internal::Isolate*, char const*, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  4: 0x1028356ac v8::internal::V8::FatalProcessOutOfMemory(v8::internal::Isolate*, char const*, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  5: 0x1029b74d4 v8::internal::Heap::GarbageCollectionReasonToString(v8::internal::GarbageCollectionReason) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  6: 0x1029b5f70 v8::internal::Heap::CollectGarbage(v8::internal::AllocationSpace, v8::internal::GarbageCollectionReason, v8::GCCallbackFlags) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  7: 0x1029c173c v8::internal::Heap::AllocateRawWithLightRetrySlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  8: 0x1029c17d0 v8::internal::Heap::AllocateRawWithRetryOrFailSlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  9: 0x102993e10 v8::internal::Factory::NewFillerObject(int, bool, v8::internal::AllocationType, v8::internal::AllocationOrigin) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 10: 0x102cd96c8 v8::internal::Runtime_AllocateInYoungGeneration(int, unsigned long*, v8::internal::Isolate*) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 11: 0x102fef8ec Builtins_CEntry_Return1_DontSaveFPRegs_ArgvOnStack_NoBuiltinExit [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 12: 0x107eb3b70

As suggested on Internet, you can increase the memory for JS, just wondering why this is necessary? I'm gonna invetstigate further

export NODE_OPTIONS="--max-old-space-size=8192"
fadeev commented 4 months ago

@lumtis I was getting the same error, then switched to nodejs v20 it's gone.

skosito commented 4 months ago

I get this error when starting localnet:

[NODE] <--- JS stacktrace --->
[NODE]
[NODE] FATAL ERROR: Reached heap limit Allocation failed - JavaScript heap out of memory
[NODE]  1: 0x1026f2984 node::Abort() [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  2: 0x1026f2b74 node::ModifyCodeGenerationFromStrings(v8::Local<v8::Context>, v8::Local<v8::Value>, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  3: 0x1028356e8 v8::Utils::ReportOOMFailure(v8::internal::Isolate*, char const*, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  4: 0x1028356ac v8::internal::V8::FatalProcessOutOfMemory(v8::internal::Isolate*, char const*, bool) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  5: 0x1029b74d4 v8::internal::Heap::GarbageCollectionReasonToString(v8::internal::GarbageCollectionReason) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  6: 0x1029b5f70 v8::internal::Heap::CollectGarbage(v8::internal::AllocationSpace, v8::internal::GarbageCollectionReason, v8::GCCallbackFlags) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  7: 0x1029c173c v8::internal::Heap::AllocateRawWithLightRetrySlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  8: 0x1029c17d0 v8::internal::Heap::AllocateRawWithRetryOrFailSlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE]  9: 0x102993e10 v8::internal::Factory::NewFillerObject(int, bool, v8::internal::AllocationType, v8::internal::AllocationOrigin) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 10: 0x102cd96c8 v8::internal::Runtime_AllocateInYoungGeneration(int, unsigned long*, v8::internal::Isolate*) [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 11: 0x102fef8ec Builtins_CEntry_Return1_DontSaveFPRegs_ArgvOnStack_NoBuiltinExit [/Users/lucas/.nvm/versions/node/v16.20.2/bin/node]
[NODE] 12: 0x107eb3b70

As suggested on Internet, you can increase the memory for JS, just wondering why this is necessary? I'm gonna invetstigate further

export NODE_OPTIONS="--max-old-space-size=8192"

thanks for checking, i didnt have this error locally

it could be that hardhat is spending a lot of resources, did you also try this https://hardhat.org/hardhat-runner/docs/troubleshooting/common-problems#out-of-memory-errors-when-compiling-large-projects

using different node version might also help as @fadeev suggested

lumtis commented 4 months ago

@fadeev I think this makes sense if you can review this one

skosito commented 4 months ago

This looks good.

Not blocking for this PR, but I would see two improvement for the developer.

  • Packaging the command to reduce the logs to what is essential to developer: showing account the two gateway addresses:
Local ZetaChain contracts environment deployed
Account 1: ...
...
Gateway EVM: 0x...
Gateway ZEVM: 0x...

Maybe could be done with some flags.

  • Even further to simplify dev development, shipping a Hardhat plugin for devs to use to integrate the gateway contracts and worker in their own localnet.
import "zeta-contracts-localnet";

function deployScript{
    // ...

    // Deploy ZetaChain contracts environment, return gateway addresses and start the work process in the background
    var gatewayZEVM, gatewayEVM = setupLocalZetaChain(...)

    // dev do their own deployment here with their contracts using gateways
    // ...
}

Not knowledgeable enough on hardhat to know if this is possible

These are not blocking for this PR, this is further work for devEx purposes

thanks for review, I fixed the comments, except hardhat plugin part, maybe we can discuss that and research options

lumtis commented 4 months ago

thanks for review, I fixed the comments, except hardhat plugin part, maybe we can discuss that and research options

For the cleaned up log, is there maybe a solution, like a flag, to just show the WORKER logs?

fadeev commented 4 months ago

This is really cool! A few thoughts.

Should this eventually move into a separate repo? Pros: we don't mix tools and protocol contracts, we don't have to explicitly exclude this code from the audit. Cons: slower iterations as protocol contracts live in one repo, localnet lives in a different repo.

Package localnet as a Hardhat task that can be imported either by the toolkit or directly by the template, so that it can be distributed a bit more easily.

Should we find a different name for this? This feels more like a simulation rather than a local network.

fadeev commented 4 months ago

Would it make sense to start testing this with the examples we have in the example-contracts repo?

skosito commented 4 months ago

thanks for review, I fixed the comments, except hardhat plugin part, maybe we can discuss that and research options

For the cleaned up log, is there maybe a solution, like a flag, to just show the WORKER logs?

yes there is a way, i added to scripts/readme.md

skosito commented 4 months ago

This is really cool! A few thoughts.

Should this eventually move into a separate repo? Pros: we don't mix tools and protocol contracts, we don't have to explicitly exclude this code from the audit. Cons: slower iterations as protocol contracts live in one repo, localnet lives in a different repo.

Package localnet as a Hardhat task that can be imported either by the toolkit or directly by the template, so that it can be distributed a bit more easily.

Should we find a different name for this? This feels more like a simulation rather than a local network.

thanks for review - i would say currently this can help us speed up development as we work on v2 contracts so until its in development phase i would say it is beneficial to stay in same repo as it would evolve with contracts

later we can discuss moving it and packaging it differently

@lumtis what do you think?

lumtis commented 4 months ago

This is really cool! A few thoughts. Should this eventually move into a separate repo? Pros: we don't mix tools and protocol contracts, we don't have to explicitly exclude this code from the audit. Cons: slower iterations as protocol contracts live in one repo, localnet lives in a different repo. Package localnet as a Hardhat task that can be imported either by the toolkit or directly by the template, so that it can be distributed a bit more easily. Should we find a different name for this? This feels more like a simulation rather than a local network.

thanks for review - i would say currently this can help us speed up development as we work on v2 contracts so until its in development phase i would say it is beneficial to stay in same repo as it would evolve with contracts

later we can discuss moving it and packaging it differently

@lumtis what do you think?

Yeah, I would tend toward keep the main command in this repo as being part of the development workflow and provide a packaged plugin or so reusable in a utility