feat(types): extend FoundString data model with non_exhaustive and builder pattern

.github/copilot-instructions.md

@@ -52,7 +52,7 @@ Convert external errors with `From` implementations. Provide offsets, section na
 
 Container parsers assign weights (1.0-10.0) to sections based on string likelihood:
 
-```rust
+```text
 // ELF example from container/elf.rs
 ".rodata" | ".rodata.str1.*" => 10.0  // Highest priority
 ".comment" | ".note.*"       => 9.0   // Build info
@@ -83,10 +83,24 @@ Use `#[non_exhaustive]` for public API structs like `ContainerInfo` and provide
 
 ```rust
 #[non_exhaustive]
-pub struct ContainerInfo { /* fields */ }
+pub struct ContainerInfo {/* fields */}
 
 impl ContainerInfo {
-    pub fn new(format: BinaryFormat, sections: Vec<SectionInfo>, ...) -> Self { ... }
+    pub fn new(
+        format: BinaryFormat,
+        sections: Vec<SectionInfo>,
+        imports: Vec<ImportInfo>,
+        exports: Vec<ExportInfo>,
+        resources: Option<Vec<ResourceMetadata>>,
+    ) -> Self {
+        Self {
+            format,
+            sections,
+            imports,
+            exports,
+            resources,
+        }
+    }
 }
 ```
 
@@ -186,7 +200,7 @@ The `justfile` uses OS annotations (`[windows]`/`[unix]`) for cross-platform com
 
 **Adding a new section weight** (in `container/elf.rs`, `pe.rs`, or `macho.rs`):
 
-```rust
+```text
 let weight = match section_name {
     ".mydata" => 8.0,  // New section type
     _ => existing_match_arms
@@ -195,7 +209,7 @@ let weight = match section_name {
 
 **Extracting strings from a section**:
 
-```rust
+```text
 use stringy::extraction::{extract_ascii_strings, AsciiExtractionConfig};
 let config = AsciiExtractionConfig { min_length: 4, max_length: 1024 };
 let strings = extract_ascii_strings(&section_data, &config);

.github/prompts/cicheck.prompt.md

@@ -0,0 +1,16 @@
+---
+agent: agent
+name: Continuous Integration Check
+description: This prompt is used to run and fix issues identified by the continuous integration check command.
+model: OpenAI GPT-5.2-Codex (copilot)
+---
+
+Run `just ci-check` and analyze any failures or warnings. If there are any issues, fix them and run the command again. Continue this process until `just ci-check` passes completely without any failures or warnings. Focus on:
+
+1. Linting errors
+2. Test failures
+3. Formatting issues
+4. Security issues
+5. ERB template issues
+
+After each fix, re-run `just ci-check` to verify the changes resolved the issues. Only stop when all checks pass successfully. Provide a summary of the changes made to fix the issues once `just ci-check` passes.

.github/prompt/simplicity-review.prompt.md → .github/prompts/simplicity-review.prompt.md

@@ -1,6 +1,13 @@
+---
+agent: agent
+name: Simplicity Review
+description: This prompt is used to review and simplify code changes by applying principles of simplicity, idiomatic coding, and test proportionality.
+model: OpenAI GPT-5.2-Codex
+---
+
 CODE SIMPLIFICATION REVIEW
 
-Start by examining the uncommitted changes in the current codebase.
+Start by examining the uncommitted changes (or the changes in the current branch if there are no uncommitted changes) in the current codebase.
 
 ANALYSIS STEPS:
 

.github/workflows/ci.yml

@@ -114,8 +114,9 @@ jobs:
           # Primary Support - Linux
           - os: ubuntu-latest
             platform: "Linux"
-          - os: arm
-            platform: "Linux"
+            #  Disabled due to lack of ARM runners on GitHub Actions, will re-enable when available
+          # - os: arm
+          #   platform: "Linux"
           # Primary Support - macOS (using available runners)
           - os: macos-latest
             platform: "macOS"
@@ -176,3 +177,48 @@ jobs:
         with:
           token: ${{ secrets.QLTY_COVERAGE_TOKEN }}
           files: target/lcov.info
+
+  # Gate job for branch protection - always runs and reports aggregate status
+  # Use this as the required status check instead of individual jobs
+  ci-gate:
+    name: CI Gate
+    runs-on: ubuntu-latest
+    needs: [quality, msrv, test, test-cross-platform, coverage]
+    if: always()
+    steps:
+      - name: Check job results
+        run: |
+          echo "Quality: ${{ needs.quality.result }}"
+          echo "MSRV: ${{ needs.msrv.result }}"
+          echo "Test: ${{ needs.test.result }}"
+          echo "Test Cross-Platform: ${{ needs.test-cross-platform.result }}"
+          echo "Coverage: ${{ needs.coverage.result }}"
+
+          # Fail if any required job failed
+          # Jobs that were skipped (due to path filters) are OK
+          if [[ "${{ needs.quality.result }}" == "failure" || "${{ needs.quality.result }}" == "cancelled" ]]; then
+            echo "::error::Quality checks failed"
+            exit 1
+          fi
+
+          if [[ "${{ needs.msrv.result }}" == "failure" || "${{ needs.msrv.result }}" == "cancelled" ]]; then
+            echo "::error::MSRV check failed"
+            exit 1
+          fi
+
+          if [[ "${{ needs.test.result }}" == "failure" || "${{ needs.test.result }}" == "cancelled" ]]; then
+            echo "::error::Tests failed"
+            exit 1
+          fi
+
+          if [[ "${{ needs.test-cross-platform.result }}" == "failure" || "${{ needs.test-cross-platform.result }}" == "cancelled" ]]; then
+            echo "::error::Cross-platform tests failed"
+            exit 1
+          fi
+
+          if [[ "${{ needs.coverage.result }}" == "failure" || "${{ needs.coverage.result }}" == "cancelled" ]]; then
+            echo "::error::Coverage generation failed"
+            exit 1
+          fi
+
+          echo "All CI checks passed (or were skipped due to no relevant changes)"

.serena/.gitignore

@@ -0,0 +1 @@
+/cache

.serena/project.yml

@@ -0,0 +1,89 @@
+# list of languages for which language servers are started; choose from:
+#   al                  bash                clojure             cpp                 csharp
+#   csharp_omnisharp    dart                elixir              elm                 erlang
+#   fortran             fsharp              go                  groovy              haskell
+#   java                julia               kotlin              lua                 markdown
+#   matlab              nix                 pascal              perl                php
+#   powershell          python              python_jedi         r                   rego
+#   ruby                ruby_solargraph     rust                scala               swift
+#   terraform           toml                typescript          typescript_vts      vue
+#   yaml                zig
+#   (This list may be outdated. For the current list, see values of Language enum here:
+#   https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py
+#   For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.)
+# Note:
+#   - For C, use cpp
+#   - For JavaScript, use typescript
+#   - For Free Pascal/Lazarus, use pascal
+# Special requirements:
+#   - csharp: Requires the presence of a .sln file in the project folder.
+#   - pascal: Requires Free Pascal Compiler (fpc) and optionally Lazarus.
+# When using multiple languages, the first language server that supports a given file will be used for that file.
+# The first language is the default language and the respective language server will be used as a fallback.
+# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored.
+languages:
+- rust
+
+# the encoding used by text files in the project
+# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings
+encoding: "utf-8"
+
+# whether to use project's .gitignore files to ignore files
+ignore_all_files_in_gitignore: true
+
+# list of additional paths to ignore in all projects
+# same syntax as gitignore, so you can use * and **
+ignored_paths: []
+
+# whether the project is in read-only mode
+# If set to true, all editing tools will be disabled and attempts to use them will result in an error
+# Added on 2025-04-18
+read_only: false
+
+# list of tool names to exclude. We recommend not excluding any tools, see the readme for more details.
+# Below is the complete list of tools for convenience.
+# To make sure you have the latest list of tools, and to view their descriptions, 
+# execute `uv run scripts/print_tool_overview.py`.
+#
+#  * `activate_project`: Activates a project by name.
+#  * `check_onboarding_performed`: Checks whether project onboarding was already performed.
+#  * `create_text_file`: Creates/overwrites a file in the project directory.
+#  * `delete_lines`: Deletes a range of lines within a file.
+#  * `delete_memory`: Deletes a memory from Serena's project-specific memory store.
+#  * `execute_shell_command`: Executes a shell command.
+#  * `find_referencing_code_snippets`: Finds code snippets in which the symbol at the given location is referenced.
+#  * `find_referencing_symbols`: Finds symbols that reference the symbol at the given location (optionally filtered by type).
+#  * `find_symbol`: Performs a global (or local) search for symbols with/containing a given name/substring (optionally filtered by type).
+#  * `get_current_config`: Prints the current configuration of the agent, including the active and available projects, tools, contexts, and modes.
+#  * `get_symbols_overview`: Gets an overview of the top-level symbols defined in a given file.
+#  * `initial_instructions`: Gets the initial instructions for the current project.
+#     Should only be used in settings where the system prompt cannot be set,
+#     e.g. in clients you have no control over, like Claude Desktop.
+#  * `insert_after_symbol`: Inserts content after the end of the definition of a given symbol.
+#  * `insert_at_line`: Inserts content at a given line in a file.
+#  * `insert_before_symbol`: Inserts content before the beginning of the definition of a given symbol.
+#  * `list_dir`: Lists files and directories in the given directory (optionally with recursion).
+#  * `list_memories`: Lists memories in Serena's project-specific memory store.
+#  * `onboarding`: Performs onboarding (identifying the project structure and essential tasks, e.g. for testing or building).
+#  * `prepare_for_new_conversation`: Provides instructions for preparing for a new conversation (in order to continue with the necessary context).
+#  * `read_file`: Reads a file within the project directory.
+#  * `read_memory`: Reads the memory with the given name from Serena's project-specific memory store.
+#  * `remove_project`: Removes a project from the Serena configuration.
+#  * `replace_lines`: Replaces a range of lines within a file with new content.
+#  * `replace_symbol_body`: Replaces the full definition of a symbol.
+#  * `restart_language_server`: Restarts the language server, may be necessary when edits not through Serena happen.
+#  * `search_for_pattern`: Performs a search for a pattern in the project.
+#  * `summarize_changes`: Provides instructions for summarizing the changes made to the codebase.
+#  * `switch_modes`: Activates modes by providing a list of their names
+#  * `think_about_collected_information`: Thinking tool for pondering the completeness of collected information.
+#  * `think_about_task_adherence`: Thinking tool for determining whether the agent is still on track with the current task.
+#  * `think_about_whether_you_are_done`: Thinking tool for determining whether the task is truly completed.
+#  * `write_memory`: Writes a named memory (for future reference) to Serena's project-specific memory store.
+excluded_tools: []
+
+# initial prompt for the project. It will always be given to the LLM upon activating the project
+# (contrary to the memories, which are loaded on demand).
+initial_prompt: ""
+
+project_name: "Stringy"
+included_optional_tools: []

Cargo.toml

@@ -3,13 +3,13 @@ name         = "stringy"
 version      = "0.1.0"
 edition      = "2024"
 rust-version = "1.91"
-authors      = [ "UncleSp1d3r <unclesp1d3r@evilbitlabs.io>" ]
+authors      = ["UncleSp1d3r <unclesp1d3r@evilbitlabs.io>"]
 description  = "A smarter alternative to the strings command that leverages format-specific knowledge"
 license      = "Apache-2.0"
 repository   = "https://github.com/EvilBit-Labs/Stringy"
 homepage     = "http://evilbitlabs.io/Stringy/"
-keywords     = [ "binary", "strings", "analysis", "reverse-engineering", "malware" ]
-categories   = [ "command-line-utilities", "development-tools" ]
+keywords     = ["binary", "strings", "analysis", "reverse-engineering", "malware"]
+categories   = ["command-line-utilities", "development-tools"]
 
 [lib]
 name = "stringy"

codebase_analysis.md

@@ -101,7 +101,7 @@
 
 Library entry point with module declarations and public re-exports.
 
-```rust
+```text
 #![forbid(unsafe_code)]
 #![deny(warnings)]
 
@@ -122,7 +122,7 @@ pub use types::{BinaryFormat, ContainerInfo, Encoding, FoundString /* ... */};
 
 CLI placeholder using `clap` derive macros.
 
-```rust
+```text
 #[derive(Parser)]
 #[command(name = "stringy")]
 struct Cli {
@@ -159,7 +159,7 @@ Core data structures with comprehensive type definitions:
 
 Defines the `ContainerParser` trait and format detection.
 
-```rust
+```text
 pub trait ContainerParser {
     fn detect(data: &[u8]) -> bool
     where
@@ -213,7 +213,7 @@ Mach-O parser for macOS/iOS binaries:
 
 Main extraction framework with `StringExtractor` trait and `BasicExtractor`.
 
-```rust
+```text
 pub trait StringExtractor {
     fn extract(&self, data: &[u8], info: &ContainerInfo) -> Vec<FoundString>;
 }
@@ -271,7 +271,7 @@ Semantic classifier with pattern matching:
 
 **N/A** - Stringy is a command-line tool, not a web service. The public API is exposed as a Rust library:
 
-```rust
+```text
 // Library usage
 use stringy::{detect_format, create_parser, BasicExtractor, SemanticClassifier};