3447 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
xunilrj	27289d1eea	fix locals offset	2025-08-04 14:11:13 -03:00
xunilrj	54f3d20200	update test	2025-08-04 13:36:42 -03:00
xunilrj	363ec6f155	udpdate tests	2025-08-01 16:54:21 -03:00
xunilrj	1bf5300691	udpdate tests	2025-08-01 16:42:12 -03:00
xunilrj	0cec896cb6	remove a.txt	2025-08-01 16:38:04 -03:00
xunilrj	bbf8aec7ac	fix sroa test	2025-08-01 16:38:04 -03:00
xunilrj	5208360965	fix sroa for arrays	2025-08-01 16:38:04 -03:00
xunilrj	700b85fd3a	update tests	2025-08-01 16:38:02 -03:00
xunilrj	6ac40797aa	move optimization for ASM generation using local initializer	2025-08-01 16:37:20 -03:00
xunilrj	ab8ec4de7f	update tests	2025-08-01 16:37:20 -03:00
xunilrj	3494eda35a	update tests	2025-08-01 16:37:18 -03:00
xunilrj	eab04bd053	fmt and clippy issues	2025-08-01 16:33:39 -03:00
xunilrj	409fc322eb	fmt and clippy issues	2025-08-01 16:33:39 -03:00
xunilrj	b855b2d986	use mcli when initializing array repeat	2025-08-01 16:33:39 -03:00
Vaivaswatha N	05e667dfc9	Remove some uses of ptr_to_int and int_to_ptr, using ptr instead (#7297) ... This is in preparation for the argument mutability analysis. This PR also has some skeleton code for this analysis, but the actual analysis is still a `todo!()`. The analysis will also have better precision if we use fewer asm blocks, but I'll get to that after working on the analysis itself.	2025-08-01 19:22:59 +10:00
zees-dev	8b29cc39c5	feat: forc-mcp auth for mcp server hosting (#7300) ... ## Description This PR introduces api-key based auth (and management endpoints for an admin account) for the `forc-mcp` HTTP server. Functionality includes: - Admin-only API key management endpoints for creating, listing, viewing, and deleting API keys - Enhanced rate limiting with separate limits for public and authenticated requests - Flexible authentication modes supporting both public access and API-key-only operation The docs have been updated with details on how to add MCP server with auth for claude and cursor. Addresses https://github.com/FuelLabs/sway/issues/7301 <details> <summary>Admin Endpoints</summary> All admin endpoints require authentication with an admin API key via `X-API-Key` header: #### `POST` `/admin/api-keys` - Creates new user-level API keys - Returns the generated API key (shown only once for security) - Generated keys use secure SHA256 hashing with `mcp_` prefix #### `GET` `/admin/api-keys` - Lists all API keys with usage statistics - Optional include_admin=true query parameter to include admin keys - Shows real-time usage counters and rate limit status #### `GET` `/admin/api-keys/{key_id}` - Retrieves details for a specific API key - Returns `404` for admin keys to maintain security - Includes current usage statistics #### `DELETE` `/admin/api-keys/{key_id}` - Deletes specific API keys - Prevents deletion of admin keys (returns 403) - Returns `204` on successful deletion #### `POST` `/admin/import` - Bulk imports API keys with historical usage data - Supports merge mode (default) or replace mode with `clear_existing: true` - Useful for migration or backup restoration </details> ### Dual-Tier Rate Limiting System #### Public Requests (no API key): - Default: `10` requests/minute, `1,000` requests/day - Tracked by client IP address #### Authenticated Requests (with API key): - Default: `120` requests/minute, `10,000` requests/day - Admin keys have unlimited access - Tracked per API key with usage persistence #### Intelligent Counter Reset Logic - Per-minute counters reset after `60` seconds - Daily counters reset at midnight (UTC date change) ### Authentication Modes - Mixed Mode (Default) - Allows both public and authenticated access - Public requests get lower rate limits - API key holders get higher rate limits - API Keys Only Mode - Set `api_keys_only: true` in configuration - Rejects all requests without valid API key - Suitable for production deployments requiring authentication ### Testing - Unit tests for authentication middleware - Integration tests for admin endpoints - Rate limiting validation tests - API key lifecycle tests (create, use, delete) - Security tests (unauthorized access, role escalation) - Persistence tests (file storage, restart recovery) ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [x] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: z <zees-dev@users.noreply.github.com> Co-authored-by: Joshua Batty <joshpbatty@gmail.com>	2025-07-31 18:13:37 +12:00
Mike Christopher	688242c07f	feat: check file descriptor limits before running forc node (#7302) ... ## Description Adds a check to try and set the `NOFILE` limit on Unix-based systems. This is important for RocksDB, since we generally exceed the default maximum number of allowed file descriptors allowed by the OS. The idea is to attempt to raise that limit to a reasonable number, and throw an error if we are unable to (likely due to user permission issues). ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers.	2025-07-31 11:31:43 +10:00
Joshua Batty	c7ff31207a	Add parallel processing to forc-doc using rayon to improve performance (#7296) ... ## Description Key changes: - Parallelize document rendering and link generation - Add type aliases for complex nested types (`DocLinkMap`, `ModuleMap`, `RenderResult`) - Remove unnecessary wrapper functions and clones The parallel processing maintains insertion order through sequential merging, ensuring identical documentation output. Not sure why the codspeed report isn't showing this below but when I run `cargo bench` locally i'm seeing these results. | Metric | Before | After | Improvement | |--------|--------|-------|-------------| | build_std_lib_docs | 70.069 ms | 43.227 ms | **43.2% faster** | ## Checklist - [ ] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-30 14:21:46 +04:00
MozirDmitriy	32dcbaa243	docs: fix broken sway-libs GitHub link to use official documentation URL (#7298) ... - Replace https://github.com/FuelLabs/sway-libs/tree/master/libs/src/ownership with https://fuellabs.github.io/sway-libs/book/ownership/index.html	2025-07-28 19:51:33 -07:00
zees-dev	4c9c4c29bf	feat: forc mcp server - with forc-call tool integration (#7284) ... ## Description Introducing Forc-MCP module (CLI). The MCP server can be run in 3 modes: - `stdio` - `sse`: long-running server - using http server-side-events - `http`: long-running server - using http streams ### Forc-call integration The first tool to be integrated is `forc-call` - which exposes the following tool calls: - `list_contract_functions` - `transfer_assets` - `get_execution_trace` - `call_contract` And the following resources: - `MCP Type Encoding Reference` - `MCP Tool Usage Examples` - `Contract Examples with MCP Tools` ### Screenshots from `@modelcontextprotocol/inspector` <img width="2543" height="549" alt="Screenshot 2025-07-15 at 5 09 16 PM" src="https://github.com/user-attachments/assets/aaab5174-d5e6-4685-be71-fd17cd4f5d0f" /> <img width="2540" height="531" alt="Screenshot 2025-07-15 at 5 09 30 PM" src="https://github.com/user-attachments/assets/9ab39d5a-950c-4404-a3a3-6e34b89f58e7" /> ### Example usage (claude code) Pre-requisites: - Run local fuel-core node ``` fuel-core run --ip 127.0.0.1 --port 4000 --db-type rocks-db --debug --historical-execution ``` - Deploy a contract to local node: `forc deploy --default-signer` 1. Run the MCP server (using http-steam in this example): ``` cargo run -p forc-mcp -- http ``` 2. Add mcp server to claude ``` claude mcp add --transport http forc-mcp-http http://localhost:3001/mcp ``` 3. Use claude/LLM to interact with MCP server <details> <summary>Claude output</summary> ``` ╭───────────────────────────────────────────────────╮ │ ✻ Welcome to Claude Code! │ │ │ │ /help for help, /status for your current setup │ │ │ │ cwd: /Users/z/Desktop/fuellabs/sway │ ╰───────────────────────────────────────────────────╯ > Use the forc-mcp-http. Given the following sway contract: demo/demo/src/main.sw deployed at the following address: ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a903464c441eb2 Using the forc-mcp-http: > list all its callable functions. > can you get the current count? > tell me how much gas it would cost to increment the count. > show me the execution trace for incrementing the count. ⎿ ⧉ Selected 14 lines from scratch/ai/templates.md in Cursor ⏺ I'll help you interact with the deployed Sway contract using forc-mcp-http. Let me start by reading the contract to understand its structure, then perform the requested operations. ⏺ Read(demo/demo/src/main.sw) ⎿ Read 34 lines (ctrl+r to expand) ⏺ Now I need to find the ABI file for this contract to use with the forc-mcp-http tools: ⏺ Search(pattern: "demo/demo/out/**/*.json") ⎿ Found 7 files (ctrl+r to expand) ⏺ Perfect! I found the ABI file and a deployment file that matches the contract address. Let me read the ABI: ⏺ Read(demo/demo/out/release/demo-abi.json) ⎿ Read 89 lines (ctrl+r to expand) ⏺ Now let me use the forc-mcp-http tools to interact with the contract. First, I'll list all callable functions: ⏺ forc-mcp-http:list_contract_functions (MCP)(abi: "/demo/demo/out/rele ase/demo-abi.json", contract_id: "ae40e8dbe366c5ac61fe55 8e4e9139300534cd5d9463522621a903464c441eb2") ⎿ Callable functions for contract: ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a903464c441eb2 get_count() -> u64 … +186 lines (ctrl+r to expand) ⏺ Now let me get the current count: ⏺ forc-mcp-http:call_contract (MCP)(abi: "/demo/demo/out/release/demo-a bi.json", contract_id: "ae40e8dbe366c5ac61fe558e4e9139300534cd5d94 63522621a903464c441eb2", function: "get_count") ⎿ { "tx_hash": "0f1e868e75530f33d37748cac9ae25c33bf166c9e02d28e36f3ffdd67ecf3584", "total_gas": 65007, … +354 lines (ctrl+r to expand) ⏺ Now let me check the gas cost for incrementing the count using dry-run mode: ⏺ forc-mcp-http:call_contract (MCP)(abi: "/demo/demo/out/release/demo-a bi.json", contract_id: "ae40e8dbe366c5ac61fe558e4e9139300534cd5d94 63522621a903464c441eb2", function: "increment_count", function_args: ["(1, 2)"], mode: "dry-run") ⎿ Error: Contract call failed: input must start with '{' and end with '}': (1, 2) ⏺ Let me fix the format for the struct argument: ⏺ forc-mcp-http:call_contract (MCP)(abi: "/demo/demo/out/release/demo-a bi.json", contract_id: "ae40e8dbe366c5ac61fe558e4e9139300534cd5d94 63522621a903464c441eb2", function: "increment_count", function_args: ["{\"vals\": [1, 2]}"], mode: "dry-run") ⎿ Error: Contract call failed: input must start with '(' and end with ')': "vals": [1, 2] ⏺ Let me try the tuple format as shown in the example: ⏺ forc-mcp-http:call_contract (MCP)(abi: "/demo/demo/out/release/demo-a bi.json", contract_id: "ae40e8dbe366c5ac61fe558e4e9139300534cd5d94 63522621a903464c441eb2", function: "increment_count", function_args: ["((1, 2))"], mode: "dry-run") ⎿ Error: Contract call failed: input must start with '{' and end with '}': ((1, 2)) ⏺ Let me try with the correct struct format: ⏺ forc-mcp-http:call_contract (MCP)(abi: "/demo/demo/out/release/demo-a bi.json", contract_id: "ae40e8dbe366c5ac61fe558e4e9139300534cd5d94 63522621a903464c441eb2", function: "increment_count", function_args: ["{(1, 2)}"], mode: "dry-run") ⎿ { "tx_hash": "f694c73230e893b00968d8106f5bafbcd585c2cf0f4aea1c6a562ce7e1868690", "total_gas": 78940, … +399 lines (ctrl+r to expand) ⏺ Perfect! Now let me get the execution trace for that increment operation: ⏺ forc-mcp-http:get_execution_trace (MCP)(total_gas: 78940, trace_events: [{"Call":{"index":0,"method ":"increment_count","arguments":["Adder { vals: (1, 2) }"],"to":"ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621 a903464c441eb2","amount":0,"gas":26222}},{"LogData":{"index" :2,"id":"ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a 903464c441eb2","value":"3","len":8}},{"ReturnData":{"index": 4,"id":"ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a9 03464c441eb2","data":"()"}},{"Return":{"index":6,"id":"00000 00000000000000000000000000000000000000000000000000000000000" ,"val":1}},{"ScriptResult":{"index":7,"result":"Success","ga s_used":22210}}]) ⎿ Traces: [Script] ├─ [26222] 0xae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a903464c441eb2:: … +8 lines (ctrl+r to expand) ⏺ Summary Here are the results for the deployed Sway contract at ae40e8dbe366c5ac61fe558e4e9139300534cd5d9463522621a903464c441eb2: Callable Functions: 1. get_count() → returns u64 (read-only) 3. increment_count(adder: Adder) → returns () (read/write storage) Current Count: The current count is 1 Gas Cost for Increment: Incrementing the count with Adder { vals: (1, 2) } costs 78,940 gas total (22,210 gas used by script) Execution Trace: The increment operation: - Calls increment_count with Adder { vals: (1, 2) } - Uses 26,222 gas for the contract call - Emits a log with value 3 (0 + 1 + 2 = 3, the new count) - Returns () (unit/void) - Total script gas used: 22,210 - Result: Success The contract adds the two values from the Adder struct (1 + 2 = 3) to the current storage count (0) and logs the result. ``` </details> ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: z <zees-dev@users.noreply.github.com>	2025-07-24 08:18:31 -07:00
Daniel Frederico Lins Leite	22d858682b	Fix const generics standalone fns (#7292) ... ## Description Continuation of https://github.com/FuelLabs/sway/issues/6860. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-23 16:31:09 +04:00
Vaivaswatha N	a5e61488da	Represent RawUntypedPtr AST type using a new Pointer IR type (#7272) ... The existing `Pointer` IR type is renamed to `TypedPointer` (to be consistent with the existing `Slice` / `TypedSlice` IR types).	2025-07-22 04:26:38 +00:00
kaya	8963312ba8	feat: add preliminary local checks for forc-publish (#7253) ... ## Description closes #7252. This pull request introduces enhancements to the `forc-publish` plugin, focusing on validating project configurations and improving error handling. Key changes include the addition of a `validate` module for preemptive checks, updates to error definitions, and modifications to the tarball creation logic to incorporate validation. New test cases and sample data directories have also been added to ensure robust validation functionality. ### Validation Enhancements: * Added a new `validate` module in `forc-publish/src/validate.rs` to check for missing `Forc.toml`, missing version fields, and unsupported dependency types. * Updated the `Error` enum in `forc-publish/src/error.rs` to include new error variants for validation failures like `InvalidForcToml`, `MissingVersionField`, and `DependencyMissingVersion`. ### Tarball Creation Updates: * Refactored `create_tarball_from_current_dir` in `forc-publish/src/tarball.rs` to use the new `validate_dir` function for preemptive validation. Removed redundant checks for `Forc.toml` existence. * Adjusted test cases in `forc-publish/src/tarball.rs` to use sample directories with predefined configurations for validation testing. [[1]](diffhunk://#diff-e3f20cadab3a1cf99fc967e0adc12e908f435a185e1529df9b152388927adf45L79-R85) [[2]](diffhunk://#diff-e3f20cadab3a1cf99fc967e0adc12e908f435a185e1529df9b152388927adf45L140-R135) ### Test Data Additions: * Added sample directories under `tests/data` for various validation scenarios, including projects with missing versions, dependencies without versions, and valid configurations. [[1]](diffhunk://#diff-b171d6da23a1fe36735cd962cfcf506831115c3714654236b31dd999c2853823R1-R11) [[2]](diffhunk://#diff-016348eaea4a95d041537b29d370619ab0d5ca99cc84f9b30d8ad561aa757a1eR1-R9) [[3]](diffhunk://#diff-0495f782769450a8c200fdcc1f29805f4811a26f4849720fa34d5b37ba45e471R1-R8) * Included `.gitignore` files in test data directories to exclude `out` and `target` folders.	2025-07-22 02:03:58 +00:00
Daniel Frederico Lins Leite	d8536d384f	Clone implementation for string arrays (#7290) ... ## Description Continuation of https://github.com/FuelLabs/sway/issues/6860. `Clone` implementation for string arrays. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-21 07:02:08 -03:00
Daniel Frederico Lins Leite	926cb4d098	Fix type check for variables in const generics (#7273) ... ## Description Fixes https://github.com/FuelLabs/sway/issues/7260. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-20 08:29:34 +04:00
Daniel Frederico Lins Leite	0339852289	Better observability for the compiler (#7250) ... ## Description Whilst finishing "const generics" I spent a LOT of time trying to find why some cases where not working. Until I found the issue on a "indirect input" for the method `type_check_method_application`. The issue is that some other method was returning a wrong value, and although the solution is not hard, there is no way to fix just this problem, and there is no way to assert this returned value to guarantee that the problem will not return. To start to improve these kind of tests, and help debug problems, this PR start to create a "callback" mechanism that allows anyone using the compiler as a library, this will not be available at the CLI, to inspect and control logging. The integration in out e2e test harness is done by the `test.toml`. ``` category = "run" expected_result = { action = "return", value = 1 } expected_result_new_encoding = { action = "return_data", value = "0000000000000001" } validate_abi = true logs = """ if pkg != "std" && event == "on_before_method_resolution" && method == "len_xxx" { print_args(); trace(true); } if pkg != "std" && event == "on_after_method_resolution" && method == "len_xxx" { print_args(); trace(false); } """ ``` The `harness` framework will not call "logs" for every callback that happens outside of the "std" library. To allow interaction with the harness itself, some commands are available: - `print_args` print all the available arguments for that event on the "snapshot"; - `trace` enables/disables trace level logging, that also end up in the "snapshot". In the example above, we will generate the following snapshot: ``` --- source: test/src/e2e_vm_tests/harness_callback_handler.rs assertion_line: 14 --- on_before_method_resolution: FromModule { method_name: len_xxx }; Regular([]); S<unresolved T -> u64, N -> 3> before get_method_safe_to_unify: S<unresolved T -> u64, N -> 3> len_xxx<N -> None>(self: unresolved Self -> S<unresolved T -> T, N -> None>): u64 -> u64 after get_method_safe_to_unify: S<unresolved T -> u64, N -> 3>; len_xxx<N -> 3>(self: unresolved Self -> S<unresolved T -> u64, N -> None>): u64 -> u64 on_after_method_resolution: FromModule { method_name: len_xxx }; Regular([]); S<unresolved T -> u64, N -> 3>; len_xxx<N -> 3>(self: unresolved Self -> S<unresolved T -> u64, N -> None>): u64 -> u64; S<unresolved T -> u64, N -> 3> on_before_method_resolution: FromModule { method_name: len_xxx }; Regular([]); S<unresolved T -> u64, N -> 3> before get_method_safe_to_unify: S<unresolved T -> u64, N -> 3> len_xxx<N -> None>(self: unresolved Self -> S<unresolved T -> T, N -> None>): u64 -> u64 after get_method_safe_to_unify: S<unresolved T -> u64, N -> 3>; len_xxx<N -> 3>(self: unresolved Self -> S<unresolved T -> u64, N -> None>): u64 -> u64 ``` The important part is that the problem I want to fix it's there. On the line of "get_method_safe_to_unify", the "self" parameter const generic argument "N" is not being materialized, although the method resolution pass started with a fully materialized type. With this callback machinery it becomes easier to debug the problems, and possible to generate asserts to internal methods. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers.	2025-07-18 07:24:32 +00:00
Igor Rončević	e303b0f1ab	Add migration for new_hashing (#7287) ... ## Description This PR: - implements "Review existing usages of `StorageMap`, `sha256`, and `keccak256`" migration step for `new_hashing` experimental feature, as described in the Breaking Changes chapter of the tracking issue #7256. - extends the migration infrastructure by providing an optional help message related to an occurrance in code. Instead of returning only `Span`, migration steps now return an `Occurrance` that combine the `Span` with an optional help message. - extends the migration infrastructure to visit all the `TyExpressionVariant`s. For some of the expressions, the typed elements are still not provided. In such cases the migration step for `new_hashing` still detects an occurrence, but the help message lacks the detailed type information. - extends the migration infrastructure to visit all the declarations relevant for the `new_hashing` migration step. E.g.; `trait`, `abi`, and `storage` decls. Additionally, the PR implements `AsRawSlice` for `str`. Here is an excerpt of an output of the migration step run on a test project: ```console info: [new_hashing] Review existing usages of `StorageMap`, `sha256`, and `keccak256` --> /src/test.sw:62:39 | ... 12 | let _ = sha256("affected"); | ---------- info: This has type "str". ... 24 | let user_metadata_key_id = sha256((user_id, key)); | -------------- info: This has type "(b256, String)", that recursively contains "Bytes". | 71 | let _ = sha256_alias(StructCRec::new()); | ----------------- info: This has type "StructCRec", that recursively contains "Vec<u8>". | ::: /src/main.sw:52:5 | ... 13 | let _ = sha256(x); | - info: This has generic type "T". Review all the concrete types used with it. | 39 | directly_affected_str_array: StorageMap<str[3], u64> = StorageMap {}, | --------------------------- info: Review this storage field, because of "str[3]" in "StorageMap" key. | 43 | nested_affected_storage_maps: StorageMap<StructA, StorageMap<raw_slice, StorageMap<EnumARec, StorageVec<StorageMap<str[3], u64>>>>> = StorageMap {}, | ---------------------------- info: Review this storage field, because of "[u8; 0]", "slice", "[u8; 0]", and "str[3]" in "StorageMap" keys. | 52 | metadata: StorageMetadata = StorageMetadata {}, | -------- info: Review this storage field, because of potential custom storage type "StorageMetadata". 56 | 72 | storage.metadata.insert(sha256(handle_name), key, value); | ----------- info: This has type "String", that contains "Bytes". | | = help: New hashing changes the hashes of instances of the following types: = help: - string slices (`str`) = help: - string arrays (`str[N]`) = help: - arrays (`[T; N]`) = help: - raw slices (`raw_slice`) = help: - vectors (`std::vec::Vec<T>`) = help: - bytes (`std::bytes::Bytes`) = help: = help: To decide if opting-in to new hashing is backward-compatible and safe or not, = help: review if those types are directly used, or are contained in types: = help: - used as keys in `StorageMap`s, = help: - used in custom storage types, = help: - hashed using `sha256` or `keccak256` functions. = help: = help: ╔═════════════════════════════════════════════════════════════════════════════════════╗ = help: ║ The above occurrences must not be seen as comprehensive, but rather as a guideline. ║ = help: ║ Carefully review all the storage access and hashing patterns in your code. ║ = help: ║ E.g., using precomputed hashes, having custom `Hash` implementations, and similar. ║ = help: ╚═════════════════════════════════════════════════════════════════════════════════════╝ = help: = help: For a detailed migration guide see: https://github.com/FuelLabs/sway/issues/7256 ``` ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-18 04:40:36 +00:00
João Matos	f117e855ea	Add #[abi_name(name = "foo")] attribute to rename ABI items. (#7057) ... ## Description Add `#[abi_name(name = "foo")]` attribute to rename enum and struct ABI items. Here is example of how it can be used: ```sway contract; #[abi_name(name = "RenamedMyStruct")] struct MyStruct {} #[abi_name(name = "RenamedMyEnum")] enum MyEnum { A: () } abi MyAbi { fn my_struct() -> MyStruct; fn my_enum() -> MyEnum; } impl MyAbi for Contract { fn my_struct() -> MyStruct { MyStruct{} } fn my_enum() -> MyEnum { MyEnum::A } } ``` Closes https://github.com/FuelLabs/sway/issues/5955. ## Remarks The checking for ABI names is being done in the ABI generation phase, which made it a requirement to change the interface of ABI checking to return Results everywhere and passing Handler all the way down, so emitted errors can be passed down to the driver for reporting. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [x] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: IGI-111 <igi-111@protonmail.com>	2025-07-17 20:12:36 -07:00
IGI-111	b68a3861db	Bump to v0.69.1 (#7289)	2025-07-17 11:48:56 -07:00
Igor Rončević	6422650f37	Add backtrace build option (#7285) ... ## Description This PR adds the `backtrace` build option as described in the [ABI Backtracing RFC](https://github.com/FuelLabs/sway-rfcs/blob/ironcev/abi-backtracing/rfcs/0016-abi-backtracing.md). This is the second step in implementing #7276. Docs for `backtrace` build option will be added in a separate PR that will document the whole backtracking feature. ## Checklist - [x] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-17 08:38:16 -07:00
Vaivaswatha N	a27d97984b	Partially revert #6795 (#7288) ... ## Description Fixes #7283	2025-07-17 11:43:26 -03:00
Hannes Karppila	74092cbbcd	Subroutine calls using the new JAL instruction (#7085) ... ## Description This PR contains an initial implementtion of subroutine calls using the in-progress [jump-and-link instruction `JAL`](https://github.com/FuelLabs/fuel-specs/pull/630). It substantially reduces the function call overhead: the old code used 4 instructions per call, while the new version uses 1-3 depending on the distance to the called function. ### Future optimizations * Reorder functions, so those that call each other are adjacent * Use absolute or IS-relative jumps where it makes sense, see https://github.com/FuelLabs/sway/issues/7267 ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [x] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [x] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-12 08:23:53 +00:00
Igor Rončević	8b7524666b	Add #[trace] attribute (#7277) ... ## Description This PR adds the `#[trace]` attribute as described in the [ABI Backtracing RFC](https://github.com/FuelLabs/sway-rfcs/blob/ironcev/abi-backtracing/rfcs/0016-abi-backtracing.md). This is the first step in implementing #7276. Docs for `#[trace]` attribute will be added in a separate PR that will document the whole backtracking feature. A check if an annotated function can actually panic will be added in a follow up PR that will implement the backtracing in the IR generation. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-11 12:35:38 +00:00
Daniel Frederico Lins Leite	384f46f61d	Contract self impl (#7275) ... ## Description Continuation of https://github.com/FuelLabs/sway/pull/7030. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: hey-ewan <ewanretorokugbe@gmail.com> Co-authored-by: ewan ✦ <66304707+hey-ewan@users.noreply.github.com> Co-authored-by: IGI-111 <igi-111@protonmail.com>	2025-07-11 11:02:37 +00:00
Igor Rončević	8d4178f12d	Implement new hashing (#7259) ... ## Description This PR implements new hashing, as explained in the tracking issue #7256. New hashing is an opt-in experimental feature with the feature flag `new_hashing`. The new hashing hashes lengths as prefix to the content hash for the following built-in and `std` types: - string slices (`str`) - arrays (`[T; N]`) - `std::vec::Vec<T>` - `std::bytes::Bytes` Some of the `std` types that use the above types internally for storing their content still hash only the content, without the length prefix of the container. The reason for this is that 1) the choice of the container is just an implementation detail and 2) the semantics of the type requires only the content (mostly of the fixed, type-specific length) to be hashed. A typical example would be `std::b512::B512` where, same to `b256` we want to hash only the content. Notice that this does not cause the security issue described in #7256. Here is the complete list of those types: - `std::crypto::secp256k1::Secp256k1` - `std::crypto::secp256r1::Secp256r1` - `std::crypto::message::Message` - `std::crypto::public_key::PublicKey` - `std::b512::B512` Some of the implementations differ based on the combination of `const_generics` and `new_hashing` features. Therefore, on CI, we have a step testing both experimental features together. Additionally, the PR: - adds missing `Hash` implementations for string arrays (`str[N]`). - adds testing of `const_generics` experimental feature to CI. ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [x] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-11 14:39:29 +12:00
kaya	403a7e5780	feat: add mdbook preprocessing for forc-publish to flatten include directives (#7264) ... ## Description closes #7263 This pull request introduces functionality to preprocess Markdown files by handling `{{#include}}` directives, enabling the inclusion of content from other files. It also integrates this functionality into the `forc-publish` plugin to process `README.md` files during tarball creation. The most important changes include the addition of the Markdown preprocessing module, updates to error handling, and modifications to the tarball creation process. ### Markdown Preprocessing Functionality: * [`forc-plugins/forc-publish/src/md_pre_process/mod.rs`](diffhunk://#diff-1d065227f3eea45f66a3189882f220de977df2e1b7d1fb2de36d2b9baeb39a7aR1-R293): Added a new module to preprocess Markdown files, including features like dependency graph construction, topological sorting, and content flattening for `{{#include}}` directives. Includes comprehensive tests for edge cases like cycles and missing includes. * [`forc-plugins/forc-publish/src/md_pre_process/error.rs`](diffhunk://#diff-2cb6edf1287489eb7edd794db5e8b727907a28755871f656cfce877aadd886c2R1-R25): Introduced a dedicated error type `MDPreProcessError` to handle issues like I/O errors, missing include files, and cycles in Markdown dependencies. ### Integration with `forc-publish` Plugin: * [`forc-plugins/forc-publish/src/lib.rs`](diffhunk://#diff-8b5115a5299062687979272a86a86b573a688194c06c044174da61798ef41574R4): Registered the new `md_pre_process` module in the plugin library. * [`forc-plugins/forc-publish/src/tarball.rs`](diffhunk://#diff-e3f20cadab3a1cf99fc967e0adc12e908f435a185e1529df9b152388927adf45R29-R31): Updated the tarball creation process to preprocess `README.md` files using the `flatten_markdown` function. Added a warning mechanism to log errors without failing the publish process. [[1]](diffhunk://#diff-e3f20cadab3a1cf99fc967e0adc12e908f435a185e1529df9b152388927adf45R29-R31) [[2]](diffhunk://#diff-e3f20cadab3a1cf99fc967e0adc12e908f435a185e1529df9b152388927adf45R44-R60) ### Error Handling Enhancements: * [`forc-plugins/forc-publish/src/error.rs`](diffhunk://#diff-d09f44c4690282b827488db75a21e561e1e6fa72d549904db3f5fc4313f4819cR34-R36): Extended the `Error` enum to include `MDPreProcessError` for better error propagation during Markdown preprocessing. ### Dependency Updates: * [`forc-plugins/forc-publish/Cargo.toml`](diffhunk://#diff-2bd34a7b1fa0f1850ad25c6e080d410b2df98c16b6cd75445a138d04e617311aR29): Added `regex` as a workspace dependency to support Markdown parsing.	2025-07-09 10:18:31 +04:00
leopardracer	5ca3dcab93	Fix Typo in Yanked Version Message (#7274) ... --- **Description:** This pull request corrects a typo in the error message and related tests, changing "avaiable" to "available" for improved clarity and professionalism.	2025-07-07 14:34:49 +04:00
zees-dev	b54fce7727	feat: forc-call inline abi support (#7270) ... ## Description This pull request introduces a enhancement to the ABI handling in the `forc-client` plugin by replacing the `Either<PathBuf, Url>` type with a new `AbiSource` enum. This improves flexibility and usability by supporting ABI sources as file paths, URLs, or raw JSON strings. Additionally, it simplifies related code and updates documentation and tests accordingly. This represents an additional optional for callers to use forc-call with an ABI available at-hand without needing to write to a file first. ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: z <zees-dev@users.noreply.github.com>	2025-07-04 08:01:13 +00:00
Joshua Batty	de2a5ac0f0	Add workspace support to forc-doc (#7268) ... ## Description Adds workspace-level documentation support to `forc doc`. When invoked from the root of a workspace, it now generates a landing page that lists all member libraries along with their descriptions extracted directly from each `Forc.toml`. Below is an example of the landing page generated when running `forc doc` at the root of the `sway-libs` workspace.  Closes https://github.com/FuelLabs/sway/issues/4103 ## Checklist - [x] I have linked to any relevant issues. - [x] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [x] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [x] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-07-04 00:40:11 -07:00
GarmashAlex	73fb34320e	Fix broken link to test data directory in README (#7266) ... ## Description Update all references in the README from the outdated src/tests/data path to the current tests/fixtures directory. This ensures that documentation and example commands accurately reflect the present project structure, preventing confusion and errors for users and contributors. ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers. Co-authored-by: kaya <20915464+kayagokalp@users.noreply.github.com>	2025-07-01 14:47:55 +00:00
kaya	f59bbd5c31	chore: use wildcard include for forc-plugins in Cargo.toml (#7265) ... ## Description Realized we can include plugins by `*` (in root `Cargo.toml`) instead of listing them explicitly which is error prone. Co-authored-by: Joshua Batty <joshpbatty@gmail.com>	2025-07-01 07:28:14 +00:00
kaya	5265dd7405	fix: typo in comment for forc-migrate (#7269) ... ## Description Unblocks the sway CI by fixing a typo in forc-migrate	2025-07-01 18:23:28 +12:00
Vaivaswatha N	0cae7a3195	treat string array values as if it were [u8; N] (#7258) ... The goal of this PR is to enable the check in the IR verifier to ensure that the operand to `ptr_to_int` instructions can only be pointers. The other changes are to support that.	2025-06-30 19:58:29 +05:30
Joshua Batty	ceedc94283	Add criterion benchmark to forc-doc + initial code quality pass (#7242) ... ## Description Doing some general code quality changes at the same time. ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers.	2025-06-30 08:34:43 +00:00
zees-dev	0ac606c132	forc-call detailed vm-interpreter call traces (#7251) ... ## Description This PR updates the `forc call` functionality to provide detailed call traces. This is achieved via retrieving `Vec<StorageReadReplayEvent>` from transactions (dry-run and/or live mode) and executing these in a vm-interpreter. - The approach is inspired by code snippets from this repo: https://github.com/FuelLabs/execution-trace ### Additional `forc-call` updates: - introduction of contract address labelling via `--label <contract-addr>:<name>` - introduction of providing additional contract abis via `--contract-abi <contract-addr>:<abi-file-or-url>` #### Example Assume the following 2 contracts - where `demo-caller` calls `demo` contract: - `demo`: `0xe84e278cb083a5b3ff871f1d3de26fdd13ae044070e1bbda18b60a13f98bb295` - `demo-caller`: `0xed4437b191cc78a02df048f21a73df37f1627efdde7d7e4232468b9de9d83485` <details> <summary>demo contract source</summary> ```sway contract; use std::{logging::log}; struct Adder { vals: (u64, u64), } abi Demo { #[storage(read)] fn get_count() -> u64; #[storage(read, write)] fn increment_count(adder: Adder); } storage { count: u64 = 0, } impl Demo for Contract { #[storage(read)] fn get_count() -> u64 { storage.count.read() + 1 } #[storage(read, write)] fn increment_count(adder: Adder) { let new_count = storage.count.read() + adder.vals.0 + adder.vals.1; storage.count.write(new_count); log(new_count); } } ``` </details> <details> <summary>demo-caller contract source</summary> ```sway contract; use std::contract_id::ContractId; struct Adder { vals: (u64, u64), } abi Demo { #[storage(read)] fn get_count() -> u64; #[storage(read, write)] fn increment_count(adder: Adder); } abi DemoCaller { #[storage(read, write)] fn call_increment_count(adder: Adder) -> u64; #[storage(read)] fn check_current_count() -> u64; } const CONTRACT_ID = 0xe84e278cb083a5b3ff871f1d3de26fdd13ae044070e1bbda18b60a13f98bb295; impl DemoCaller for Contract { #[storage(read, write)] fn call_increment_count(adder: Adder) -> u64 { let demo = abi(Demo, CONTRACT_ID); demo.increment_count(adder); log("incremented count"); log(demo.get_count()); log("done"); demo.increment_count(Adder { vals: (5, 2) }); demo.get_count() } #[storage(read)] fn check_current_count() -> u64 { let demo = abi(Demo, CONTRACT_ID); demo.get_count() } } ``` </details> **Previous functionality**: ```sh cargo run -p forc-client --bin forc-call -- \ --abi ./demo/demo-caller/out/release/demo-caller-abi.json \ ed4437b191cc78a02df048f21a73df37f1627efdde7d7e4232468b9de9d83485 \ call_increment_count "{(1,1)}" -vvv ``` **Output**: <img width="721" alt="Screenshot 2025-06-24 at 12 14 53 PM" src="https://github.com/user-attachments/assets/2ef77293-54eb-46c3-989a-b7f8cf9d236c" /> **Updated functionality**: ```sh cargo run -p forc-client --bin forc-call -- \ --abi ./demo/demo-caller/out/release/demo-caller-abi.json \ ed4437b191cc78a02df048f21a73df37f1627efdde7d7e4232468b9de9d83485 \ --contract-abi e84e278cb083a5b3ff871f1d3de26fdd13ae044070e1bbda18b60a13f98bb295:./demo/demo/out/release/demo-abi.json \ --label ed4437b191cc78a02df048f21a73df37f1627efdde7d7e4232468b9de9d83485:demo-caller \ --label e84e278cb083a5b3ff871f1d3de26fdd13ae044070e1bbda18b60a13f98bb295:demo \ call_increment_count "{(1,1)}" -vv ``` **Output**: <img width="760" alt="Screenshot 2025-06-24 at 12 15 25 PM" src="https://github.com/user-attachments/assets/442c0a97-80f8-46b6-bdf9-d67952c28b58" /> ### Other misc. improvements to `forc-call` - refactor of the forc-call verbosity levels and functions (arguably cleaner code) - re-write of the tracing to simply process receipts and indent via stack - instead of recursively constructing node-call tree - closes https://github.com/FuelLabs/sway/issues/7197 ## AI description This pull request introduces significant enhancements to the `forc call` functionality, improving usability, debugging, and trace readability for multi-contract interactions. The changes include support for labeled contract addresses, additional ABI files for better decoding, and updates to verbosity levels. Additionally, dependencies and internal parsing logic have been updated to support these features. ### Enhancements to `forc call` functionality: * **Support for labeled contract addresses:** - Added the `--label` flag to allow users to assign human-readable labels to contract addresses in transaction traces, improving readability. [[1]](diffhunk://#diff-466e2f9659cab303594eb73a846768ecdbc1a13030e5869cdac51ddde87dd313R289-R302) [[2]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bR248-R320) - Updated documentation to include examples of using labels in traces. [[1]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bR63-R73) [[2]](diffhunk://#diff-466e2f9659cab303594eb73a846768ecdbc1a13030e5869cdac51ddde87dd313R184-R193) * **Support for additional ABIs:** - Introduced the `--contract-abi` flag to specify additional contract ABIs for decoding function signatures, parameters, and return values in multi-contract interactions. [[1]](diffhunk://#diff-466e2f9659cab303594eb73a846768ecdbc1a13030e5869cdac51ddde87dd313R289-R302) [[2]](diffhunk://#diff-466e2f9659cab303594eb73a846768ecdbc1a13030e5869cdac51ddde87dd313R209-R217) - Updated the parsing logic to handle additional ABIs and labels. - Documentation now includes examples and explanations for using additional ABIs. [[1]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bR102-R115) [[2]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bR248-R320) * **Improved verbosity and tracing:** - Adjusted verbosity levels to make transaction traces available at `-vv` instead of `-vvv`. - Enhanced trace output to include labeled contract addresses and decoded function information. [[1]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bL253-R333) [[2]](diffhunk://#diff-4ee92d729fce66f7e7aed1fc29b41834951eb63198e0da747b9b9e45d13f717bR357-R413) ### Dependency and internal updates: * **Dependency additions:** - Added `fuel-core-storage` as a dependency in `Cargo.toml` to support new features. [[1]](diffhunk://#diff-2e9d962a08321605940b5a657135052fbcef87b5e360662bb527c96d9a615542R93) [[2]](diffhunk://#diff-f0f5128eecb15714bd0a80d1f03d87a84f375d0598471bb27e3bb388c188550cR49) * **Parsing and execution logic:** - Refactored `forc-client` to include reusable functions for parsing ABIs and labels. - Updated the `call_function` logic to handle additional ABIs and integrate with the new dry-run execution method. [[1]](diffhunk://#diff-7da99987eeed69f070b781a5692d3acc7028308b8538ca129d79452ccc057fdeR54-R64) [[2]](diffhunk://#diff-7da99987eeed69f070b781a5692d3acc7028308b8538ca129d79452ccc057fdeL137-R172) ## Checklist - [ ] I have linked to any relevant issues. - [ x] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [x] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: z <zees-dev@users.noreply.github.com> Co-authored-by: kaya <20915464+kayagokalp@users.noreply.github.com>	2025-06-30 19:14:25 +12:00
Joshua Batty	c37dc92952	remove archived forc-explore plugin from CI and docs (#7257) ... ## Description This repo was [archived ](https://github.com/FuelLabs/forc-explorer )in July 2024 but was not removed from CI or the docs. I have update the plugins section of the documentation from forc explore to `forc-install` which is a [tool](https://github.com/DarthBenro008/forc-install) from a community member. ## Checklist - [x] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [x] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-06-27 12:53:25 +00:00
Vaivaswatha N	586a968ef1	support __addr_of for all types (#7255)	2025-06-27 15:33:42 +12:00
zees-dev	5c22e33987	Bump/0.69.0 (#7248) ... ## Description This pull request updates the version of all workspace packages and dependencies from `0.68.9` to `0.69.0` in preparation for a new release. ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: z <zees-dev@users.noreply.github.com> Co-authored-by: IGI-111 <igi-111@protonmail.com>	2025-06-23 19:25:04 +04:00
Igor Rončević	3b5e7a8d9b	Add docs for error handling (ABI errors, panic, error_type, error) (#7249) ... ## Description This PR: - Adds a new "Error handling" page to "Sway Language Basics". - Updates all references to ABI errors. - Extends the "Breaking Release Checklist" with documentation related checks. ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [x] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [x] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [x] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [x] I have requested a review from the relevant team or maintainers.	2025-06-23 13:15:50 +00:00
IGI-111	5064247397	Stabilize ABI errors (#7241) ... ## Description Stabilize the `error_type` feature. Fixes #6765 ## Checklist - [ ] I have linked to any relevant issues. - [ ] I have commented my code, particularly in hard-to-understand areas. - [ ] I have updated the documentation where relevant (API docs, the reference, and the Sway book). - [ ] If my change requires substantial documentation changes, I have [requested support from the DevRel team](https://github.com/FuelLabs/devrel-requests/issues/new/choose) - [ ] I have added tests that prove my fix is effective or that my feature works. - [ ] I have added (or requested a maintainer to add) the necessary `Breaking*` or `New Feature` labels where relevant. - [ ] I have done my best to ensure that my PR adheres to [the Fuel Labs Code Review Standards](https://github.com/FuelLabs/rfcs/blob/master/text/code-standards/external-contributors.md). - [ ] I have requested a review from the relevant team or maintainers. --------- Co-authored-by: Igor Rončević <ironcev@hotmail.com>	2025-06-23 10:37:35 +00:00