diff --git a/docs/blog/act-via-code.mdx b/docs/blog/act-via-code.mdx deleted file mode 100644 index 1def0bc2e..000000000 --- a/docs/blog/act-via-code.mdx +++ /dev/null @@ -1,116 +0,0 @@ ---- -title: "Act via Code" -icon: "code" -iconType: "solid" -description: "Giving agents a more expressive way to act" ---- - - - - - - -Two and a half years since the launch of the GPT-3 API, code assistants have emerged as potentially the premier use case of LLMs. The rapid adoption of AI-powered IDEs and prototype builders isn't surprising — code is structured, deterministic, and rich with patterns, making it an ideal domain for machine learning. Developers actively working with tools like Cursor (myself included) have an exhiliarating yet uncertain sense that the field of software engineering is approaching an inflection point. - -Yet there's a striking gap between understanding and action for today's code assistants. When provided proper context, frontier LLMs can analyze massive enterprise codebases and propose practical paths towards sophisticated, large-scale improvements. But implementing changes that impact more than a small set of files with modern AI assistants is fundamentally infeasible. The good news is that for focused, file-level changes, we've found real success: AI-powered IDEs ([Windsurf](https://codeium.com/windsurf), [Cursor](https://www.cursor.com/)) are transforming how developers write and review code, while chat-based assistants are revolutionizing how we bootstrap and prototype new applications (via tools like [v0](https://v0.dev/), [lovable.dev](https://lovable.dev/), and [bolt.new](https://bolt.new/)). - -However, there's a whole class of critical engineering tasks that remain out of reach - tasks that are fundamentally programmatic and deal with codebase structure at scale. A significant amount of effort on modern engineering teams is directed towards eliminating tech debt, managing large-scale migrations, analyzing dependency graphs, enforcing type coverage across the codebase, and similar tasks that require a global view of a codebase. Today's AI assistants can fully understand these challenges and even propose solutions, but they lack the mechanisms to actually implement them. The intelligence is there, but it's trapped in your IDE's text completion window. - - -The bottleneck isn't intelligence — it's tooling. The solution requires letting AI systems programmatically interact with codebases and software systems through code execution environments. Code execution environments represent the most expressive tool we could offer an agent—enabling composition, abstraction, and systematic manipulation of complex systems. By combining code execution environments with custom APIs that correspond to powerful large-scale operations, we can unlock a new set of tasks in which agents can be significant contributors. When paired with ever-improving foundation models, this will lead to a step function improvement for code assistants, enabling their application in an entirely new set of valuable tasks. - -## Beating Minecraft with Code Execution - -In mid-2023, a research project called [Voyager](https://voyager.minedojo.org) made waves: it effectively solved Minecraft, performing several multiples better than the prior SOTA. This was a massive breakthrough as previous reinforcement learning systems had struggled for years with even basic Minecraft tasks. - -While the AI community was focused on scaling intelligence, Voyager demonstrated something more fundamental: the right tools can unlock entirely new tiers of capability. The same GPT-4 model that struggled with Minecraft using standard agentic frameworks (like [ReAct](https://klu.ai/glossary/react-agent-model)) achieved remarkable results when allowed to write and execute code. This wasn't about raw intelligence—it was about giving the agent a more expressive way to act. - - - - - -The breakthrough came from a simple yet powerful insight: let the AI write code. Instead of limiting the agent to primitive "tools," Voyager allowed GPT-4 to write and execute [JS programs](https://github.com/MineDojo/Voyager/tree/main/skill_library/trial2/skill/code) that controlled Minecraft actions through a clean API. - -```javascript -// Example "action program" from Voyager, 2023 -// written by gpt-4 -async function chopSpruceLogs(bot) { - const spruceLogCount = bot.inventory.count(mcData.itemsByName.spruce_log.id); - const logsToMine = 3 - spruceLogCount; - if (logsToMine > 0) { - bot.chat("Chopping down spruce logs..."); - await mineBlock(bot, "spruce_log", logsToMine); - bot.chat("Chopped down 3 spruce logs."); - } else { - bot.chat("Already have 3 spruce logs in inventory."); - } -} -``` - -This approach transformed the agent's capabilities. Rather than being constrained to atomic actions like `equipItem(...)` (this would be typical of "traditional" agent algorithms, such as ReAct), it could create higher-level operations like [craftShieldWithFurnace()](https://github.com/MineDojo/Voyager/blob/main/skill_library/trial2/skill/code/craftShieldWithFurnace.js) through composing the atomic APIs. Furthermore, Wang et al. implemented a memory mechanism, in which these successful "action programs" could later be recalled, copied, and built upon, effectively enabling the agent to accumulate experience. - - - - - -As the Voyager authors noted: - -*"We opt to use code as the action space instead of low-level motor commands because programs can naturally represent temporally extended and compositional actions, which are essential for many long-horizon tasks in Minecraft."* - -## Code is an Ideal Action Space - -What these authors demonstrated is a fundamental insight that extends far beyond gaming. Letting AI act through code rather than atomic commands will lead to a step change in the capabilities of AI systems. Nowhere is this more apparent than in software engineering, where agents already understand complex transformations but lack the tools to execute them effectively. - -Today's productionized code assistants operate though an interface where they can directly read/write to text files and perform other bespoke activities, like searching through file embeddings or running terminal commands. - -In the act via code paradigm, all of these actions are expressed through writing and executing code, like the below: - -```python -# Implement `grep` via for loops and if statements -for function in codebase.functions: - if 'Page' in function.name: - - # Implement systematic actions, like moving things around, through an API - function.move_to_file('/pages/' + function.name + '.tsx') -``` - -Provided a sufficiently comprehensive set of APIs, this paradigm has many clear advantages: - -- **API-Driven Extensibility**: Any operation that can be expressed through an API becomes accessible to the agent. This means the scope of tasks an agent can handle grows with our ability to create clean APIs for complex operations. - -- **Programmatic Efficiency**: Many agent tasks involve systematic operations across large codebases. Expressing these as programs rather than individual commands dramatically reduces computational overhead and allows for batch operations. - -- **Composability**: Agents can build their own tools by combining simpler operations. This aligns perfectly with LLMs' demonstrated ability to compose and interpolate between examples to create novel solutions. - -- **Constrained Action Space**: Well-designed APIs act as guardrails, making invalid operations impossible to express. The type system becomes a powerful tool for preventing entire classes of errors before they happen. - -- **Objective Feedback**: Code execution provides immediate, unambiguous feedback through stack traces and error messages—not just confidence scores. This concrete error signal is invaluable for learning. - -- **Natural Collaboration**: Programs are a shared language between humans and agents. Code explicitly encodes reasoning in a reviewable format, making actions transparent, debuggable, and easily re-runnable. - -## Code Manipulation Programs - -For software engineering, we believe the path forward is clear: agents need a framework that matches how developers think about and manipulate code. While decades of static analysis work gives us a strong foundation, traditional code modification frameworks weren't designed with AI-human collaboration in mind - they expose low-level APIs that don't match how developers (or AI systems) think about code changes. - -We're building a framework with high-level APIs that correspond to how engineers actually think about code modifications. The APIs are clean and intuitive, following clear [principles](/introduction/guiding-principles) that eliminate sharp edges and handle edge cases automatically. Most importantly, the framework encodes rich structural understanding of code. Consider this example: - -```python -# Access to high-level semantic operations -for component in codebase.jsx_components: - # Rich structural analysis built-in - if len(component.usages) == 0: - # Systematic operations across the codebase - component.rename(component.name + 'Page') -``` - -This isn't just string manipulation - the framework understands React component relationships, tracks usage patterns, and can perform complex refactors while maintaining correctness. By keeping the codebase representation in memory, we can provide lightning-fast operations for both analysis and systematic edits. - -The documentation for such a framework isn't just API reference - it's education for advanced intelligence about how to successfully manipulate code at scale. We're building for a future where AI systems are significant contributors to codebases, and they need to understand not just the "how" but the "why" behind code manipulation patterns. - -Crucially, we believe these APIs will extend beyond the codebase itself into the broader software engineering ecosystem. When agents can seamlessly interact with tools like Datadog, AWS, and other development platforms through the same clean interfaces, we'll take a major step toward [autonomous software engineering](/introduction/about#our-mission). The highest leverage move isn't just giving agents the ability to modify code - it's giving them programmatic access to the entire software development lifecycle. - -## Codegen is now OSS - -We're excited to release [Codegen](https://github.com/codegen-sh/codegen) as open source [Apache 2.0](https://github.com/codegen-sh/codegen/blob/develop/LICENSE) and build out this vision with the broader developer community. [Get started with Codegen](/introduction/getting-started) today or please join us in our [Slack community](https://community.codegen.com) if you have feedback or questions about a use case! - -Jay Hack, Founder \ No newline at end of file diff --git a/docs/blog/codemod-frameworks.mdx b/docs/blog/codemod-frameworks.mdx deleted file mode 100644 index f9c42ad16..000000000 --- a/docs/blog/codemod-frameworks.mdx +++ /dev/null @@ -1,228 +0,0 @@ ---- -title: "Comparing Codemod Frameworks" -sidebarTitle: "Codemod Frameworks" -icon: "code-compare" -iconType: "solid" ---- - -# Others to add -- [Abracadabra](https://github.com/nicoespeon/abracadabra) -- [Rope](https://rope.readthedocs.io/en/latest/overview.html#rope-overview) -- [Grit](https://github.com/getgrit/gritql) - -Code transformation tools have evolved significantly over the years, each offering unique approaches to programmatic code manipulation. Let's explore the strengths and limitations of major frameworks in this space. - -## Python's AST Module - -Python's built-in Abstract Syntax Tree (AST) module provides the foundation for Python code manipulation. - -### Strengths - -- Native Python implementation -- No external dependencies -- Full access to Python's syntax tree -- Great for Python-specific transformations - -### Limitations - -- Python-only -- Low-level API requiring deep AST knowledge -- Manual handling of formatting and comments -- No cross-file awareness - -```python -import ast - -class NameTransformer(ast.NodeTransformer): - def visit_Name(self, node): - if node.id == 'old_name': - return ast.Name(id='new_name', ctx=node.ctx) - return node -``` - -## LibCST - -Meta's Concrete Syntax Tree library offers a more modern approach to Python code modification. - -### Strengths - -- Preserves formatting and comments -- Type annotations support -- Visitor pattern API -- Excellent documentation -- Supports codemods at scale - -### Limitations - -- Python-only -- Steeper learning curve -- Slower than raw AST manipulation -- Memory-intensive for large codebases - -```python -import libcst as cst - -class NameTransformer(cst.CSTTransformer): - def leave_Name(self, original_node, updated_node): - if original_node.value == "old_name": - return updated_node.with_changes(value="new_name") - return updated_node -``` - -## jscodeshift - -The pioneer of JavaScript codemods, jscodeshift remains a staple in the JS ecosystem. - -### Strengths - -- Robust JavaScript/TypeScript support -- Rich ecosystem of transforms -- Familiar jQuery-like API -- Battle-tested at scale - -### Limitations - -- JavaScript/TypeScript only -- Limited type information -- Can be verbose for simple transforms -- Documentation could be better - -```javascript -export default function transformer(file, api) { - const j = api.jscodeshift; - return j(file.source) - .find(j.Identifier) - .filter((path) => path.node.name === "old_name") - .replaceWith((path) => j.identifier("new_name")) - .toSource(); -} -``` - -## ts-morph - -A TypeScript-first transformation tool with rich type system integration. - -### Strengths - -- First-class TypeScript support -- Excellent type information access -- High-level, intuitive API -- Great documentation -- Project-wide analysis capabilities - -### Limitations - -- TypeScript/JavaScript only -- Higher memory usage -- Can be slower for large projects -- More complex setup than alternatives - -```typescript -import { Project } from "ts-morph"; - -const project = new Project(); -project.addSourceFileAtPath("src/**/*.ts"); -project.getSourceFiles().forEach((sourceFile) => { - sourceFile - .getDescendantsOfKind(SyntaxKind.Identifier) - .filter((node) => node.getText() === "old_name") - .forEach((node) => node.replaceWithText("new_name")); -}); -``` - -## ast-grep - -A modern, language-agnostic code searching and rewriting tool. - -### Strengths - -- Multi-language support -- Fast pattern matching -- Simple YAML-based rules -- Great for quick transformations -- Excellent performance - -### Limitations - -- Limited complex transformation support -- Newer, less battle-tested -- Smaller ecosystem -- Less granular control - -```yaml -rules: - - pattern: old_name - replace: new_name -``` - -## tree-sitter - -The foundation many modern tools build upon, offering lightning-fast parsing and analysis. - -### Strengths - -- Incredible performance -- Multi-language support -- Incremental parsing -- Language-agnostic design -- Growing ecosystem - -### Limitations - -- Lower-level API -- Requires language-specific grammars -- Manual handling of transformations -- Steeper learning curve - -```javascript -const Parser = require("tree-sitter"); -const JavaScript = require("tree-sitter-javascript"); - -const parser = new Parser(); -parser.setLanguage(JavaScript); -const tree = parser.parse('console.log("Hello")'); -``` - -## Choosing the Right Tool - -The choice of codemod framework depends heavily on your specific needs: - -- **Single Language Focus**: If you're working exclusively with one language, use its specialized tools: - - - Python → LibCST - - TypeScript → ts-morph - - JavaScript → jscodeshift - -- **Multi-Language Projects**: Consider: - - - ast-grep for simple transformations - - tree-sitter for building custom tools - - A combination of specialized tools - -- **Scale Considerations**: - - Small projects → Any tool works - - Medium scale → Language-specific tools - - Large scale → Need proper tooling support (LibCST, ts-morph) - -## The Future of Codemods - -As codebases grow and AI becomes more prevalent, we're seeing a shift toward: - -1. **More Intelligent Tools** - - - Better type awareness - - Improved cross-file analysis - - AI-assisted transformations - -2. **Universal Approaches** - - - Language-agnostic frameworks - - Unified transformation APIs - - Better interoperability - -3. **Enhanced Developer Experience** - - Simpler APIs - - Better debugging tools - - Richer ecosystems - -The ideal codemod framework of the future will likely combine the best aspects of current tools: the type awareness of ts-morph, the simplicity of ast-grep, the performance of tree-sitter, and the reliability of LibCST. diff --git a/docs/blog/devin.mdx b/docs/blog/devin.mdx deleted file mode 100644 index 25eb50beb..000000000 --- a/docs/blog/devin.mdx +++ /dev/null @@ -1,92 +0,0 @@ ---- -title: "SWE Agents are Better with Codemods" -sidebarTitle: "Devin" -icon: "robot" -iconType: "solid" ---- - -Coding assistants like Cursor have brought us into a new era of programming. But there's a class of programming tasks that remain outside their reach: large-scale, systematic modifications across large codebases. You wouldn't ask an AI to delete all your dead code or reorganize your entire component hierarchy - the tooling just isn't there. - -That's where codemods come in. A codemod is a program that operates on a codebase, and when you give an AI agent the ability to write and execute them, these platform-level tasks fall below the high-water mark of AI capabilities. - -Here's a real example: we asked [Devin](https://docs.devin.ai/get-started/devin-intro) (an autonomous SWE agent) to "delete all dead code" from our codebase. Instead of trying to make hundreds of individual edits, Devin [wrote and debugged a program](https://github.com/codegen-sh/codegen/pull/660/files#diff-199b0c459adf1639f664fed248fa48bb640412aeacbe61cd89475d6598284b5f) that systematically removed unused code while handling edge cases like tests, decorators and indirect references. - -- [View the PR](https://github.com/codegen-sh/codegen/pull/660) -- [View on Devin](https://app.devin.ai/sessions/a49eac87da644fa9ac1144fe130b847e) - - - - - -This modifies over 40 files and correctly removes old code, passes lint + tests, etc. - -What made this work? - -Devin operates like a state machine: write a codemod, run it through the linter, analyze failures, and refine. Each iteration adds handling for new edge cases until the codemod successfully transforms the entire codebase. This is the same cycle developers use for many large-scale refactors, just automated. - -```mermaid -flowchart LR - style EditRun fill:#ff6b6b,stroke:#000,stroke-width:3px,color:#000,font-weight:bold,font-size:16px - style Linter fill:#4dabf7,stroke:#000,stroke-width:3px,color:#000,font-weight:bold,font-size:16px - style Success fill:#cc5de8,stroke:#000,stroke-width:3px,color:#000,font-weight:bold,font-size:16px - - EditRun["Edit + Run
Codemod"] --> Linter["Run
Linter"] - Linter --"success?"--- Success["Success"] - Linter --"errors found"--- EditRun - - linkStyle default stroke-width:2px - classDef edgeLabel fill:#e9ecef,color:#000,font-weight:bold - class success?,errors edgeLabel -``` - -The nice part about this approach is that we don't have to blindly trust the AI. There's no magic - it's just a program we can run and verify through linter/test output. The codemod is easy to review, and we can update it if we need to add exceptions or edge cases. Much better than trying to manually review hundreds of individual edits. - -## Try it yourself - -Want to experience this with your own Devin instance? Install the Codegen CLI in your Devin box: - -```bash -uv tool install codegen --python 3.13 -``` - -Then use the following prompt: - - - Download System Prompt - - -Or try it with other platform-level modifications supported by Codegen: - - - - Automatically convert Promise chains to async/await syntax across your codebase. - - - Move and organize code safely with automatic import and dependency handling. - - - Convert class components to hooks, standardize props, and organize components. - - - Automatically convert unittest test suites to modern pytest style. - - - -We'd love to hear how it works for you! Let us know in our [community](https://community.codegen.com) and share your experience developing codemods with Devin or other code assistants. \ No newline at end of file diff --git a/docs/blog/fixing-import-loops.mdx b/docs/blog/fixing-import-loops.mdx deleted file mode 100644 index 2db23159f..000000000 --- a/docs/blog/fixing-import-loops.mdx +++ /dev/null @@ -1,159 +0,0 @@ ---- -title: "Import Loops in PyTorch" -icon: "arrows-rotate" -iconType: "solid" -description: "Identifying and visualizing import loops in the PyTorch codebase" ---- - -In this post, we will visualize all import loops in the [PyTorch](https://github.com/pytorch/pytorch) codebase, propose a fix for one potentially unstable case, and use Codegen to refactor that fix. - - -You can find the complete jupyter notebook in our [examples repository](https://github.com/codegen-sh/codegen/tree/develop/codegen-examples/examples/removing_import_loops_in_pytorch). - - -Import loops (or circular dependencies) occur when two or more Python modules depend on each other, creating a cycle. For example: - -```python -# module_a.py -from module_b import function_b - -# module_b.py -from module_a import function_a -``` - -While Python can handle some import cycles through its import machinery, they can lead to runtime errors, import deadlocks, or initialization order problems. - -Debugging import cycle errors can be a challenge, especially when they occur in large codebases. However, Codegen allows us to identify these loops through our visualization tools and fix them very deterministically and at scale. - - - - - - - -## Visualize Import Loops in PyTorch - -Using Codegen, we discovered several import cycles in PyTorch's codebase. The code to gather and visualize these loops is as follows: - -```python -G = nx.MultiDiGraph() - -# Add all edges to the graph -for imp in codebase.imports: - if imp.from_file and imp.to_file: - edge_color = "red" if imp.is_dynamic else "black" - edge_label = "dynamic" if imp.is_dynamic else "static" - - # Store the import statement and its metadata - G.add_edge( - imp.to_file.filepath, - imp.from_file.filepath, - color=edge_color, - label=edge_label, - is_dynamic=imp.is_dynamic, - import_statement=imp, # Store the whole import object - key=id(imp.import_statement), - ) -# Find strongly connected components -cycles = [scc for scc in nx.strongly_connected_components(G) if len(scc) > 1] - -print(f" Found {len(cycles)} import cycles:") -for i, cycle in enumerate(cycles, 1): - print(f"\nCycle #{i}:") - print(f"Size: {len(cycle)} files") - - # Create subgraph for this cycle to count edges - cycle_subgraph = G.subgraph(cycle) - - # Count total edges - total_edges = cycle_subgraph.number_of_edges() - print(f"Total number of imports in cycle: {total_edges}") - - # Count dynamic and static imports separately - dynamic_imports = sum(1 for u, v, data in cycle_subgraph.edges(data=True) if data.get("color") == "red") - static_imports = sum(1 for u, v, data in cycle_subgraph.edges(data=True) if data.get("color") == "black") - - print(f"Number of dynamic imports: {dynamic_imports}") - print(f"Number of static imports: {static_imports}") -``` - -Here is one example visualized ⤵️ - - - - - -Not all import cycles are problematic! Some cycles using dynamic imports can work perfectly fine: - - - Valid import loop example - - - -PyTorch prevents most circular import issues through dynamic imports which can be seen through the `import_symbol.is_dynamic` property. If any edge in a strongly connected component is dynamic, runtime conflicts are typically resolved. - -However, we discovered an import loop worth investigating between [flex_decoding.py](https://github.com/pytorch/pytorch/blob/main/torch/_inductor/kernel/flex_decoding.py) and [flex_attention.py](https://github.com/pytorch/pytorch/blob/main/torch/_inductor/kernel/flex_attention.py): - -Invalid import loop example - -`flex_decoding.py` imports `flex_attention.py` *twice* — once dynamically and once at top-level. This mixed static/dynamic import pattern from the same module creates potential runtime instability. - -*Thus, we propose the following refactoring using Codegen*: - -## Move Shared Code to a Separate `utils.py` File - -```python -# Create new utils file -utils_file = codebase.create_file("torch/_inductor/kernel/flex_utils.py") - -# Get the two files involved in the import cycle -decoding_file = codebase.get_file("torch/_inductor/kernel/flex_decoding.py") -attention_file = codebase.get_file("torch/_inductor/kernel/flex_attention.py") -attention_file_path = "torch/_inductor/kernel/flex_attention.py" -decoding_file_path = "torch/_inductor/kernel/flex_decoding.py" - -# Track symbols to move -symbols_to_move = set() - -# Find imports from flex_attention in flex_decoding -for imp in decoding_file.imports: - if imp.from_file and imp.from_file.filepath == attention_file_path: - # Get the actual symbol from flex_attention - if imp.imported_symbol: - symbols_to_move.add(imp.imported_symbol) - -# Move identified symbols to utils file -for symbol in symbols_to_move: - symbol.move_to_file(utils_file) - -print(f" Moved {len(symbols_to_move)} symbols to flex_utils.py") -for symbol in symbols_to_move: - print(symbol.name) -``` - -Running this codemod will move all the shared symbols to a separate `utils.py` as well as resolve the imports from both files to point to the newly created file solving this potential unpredictable error that could lead issues later on. - - -## Conclusion - -Import loops are a common challenge in large Python codebases. Using Codegen, no matter the repo size, you will gain some new insights into your codebase's import structure and be able to perform deterministic manipulations saving developer hours and future runtime errors. - -Want to try it yourself? Check out our [complete example](https://github.com/codegen-sh/codegen/tree/develop/codegen-examples/examples/removing_import_loops_in_pytorch) of fixing import loops using Codegen. diff --git a/docs/blog/posts.mdx b/docs/blog/posts.mdx deleted file mode 100644 index ad92465be..000000000 --- a/docs/blog/posts.mdx +++ /dev/null @@ -1,33 +0,0 @@ ---- -title: "All Posts" -icon: "clock" -iconType: "solid" ---- - - - -## Agents are Better with Codemods - -How AI agents like Devin can use codemods to safely make systematic changes across entire codebases, from deleting dead code to modernizing React components. - - - - - - - -## Act via Code - -Why code as an action space will lead to a step function improvement in agent capabilities. - - - - diff --git a/docs/blog/promise-to-async-await-twilio.mdx b/docs/blog/promise-to-async-await-twilio.mdx deleted file mode 100644 index 6fd59bccc..000000000 --- a/docs/blog/promise-to-async-await-twilio.mdx +++ /dev/null @@ -1,168 +0,0 @@ ---- -title: "Promise -> Async/Await in Twilio Node.js SDK" -sidebarTitle: "Promise -> Async/Await" -description: "Using Codegen to automate the conversion of ***592 instances*** of Promise `.then` chains to `async/await` in Twilio's Node.js Repository" -icon: "hand-fingers-crossed" -iconType: "solid" ---- - - - -Promise `.then()` chains often lead to nested, hard-to-read code. While `async/await` offers a cleaner alternative, migrating large codebases like [Twilio's Node.js SDK](https://github.com/twilio/twilio-node) requires careful handling of backward compatibility. - - -Using Codegen, we performed this conversion reliably across **all 592 instances.** - - -Here is the conversion [Pull Request](https://github.com/twilio/twilio-node/pull/1072) made using Codegen. - - -## The Pattern - - Twilio's Node.js SDK has [this](https://github.com/twilio/twilio-node/blob/9bc36951e300af5affff46a05bdd120c7d6ceec4/src/rest/accounts/v1/credential/aws.ts#L182) Promise chain pattern repeated across the codebase: - - - -```typescript -function update(callback?: (error: Error | null, item?: Instance) => any): Promise { - let operationPromise = operationVersion.update({ - uri: instance._uri, - method: "post", - headers, - }); - - operationPromise = operationPromise.then( - (payload) => new Instance(operationVersion, payload) - ); - - operationPromise = instance._version.setPromiseCallback( - operationPromise, - callback - ); - return operationPromise; -} -``` - -Each instance of this is found: -1. Creating an `operationPromise` -2. Transforming the response -3. Handling callbacks through `setPromiseCallback` -4. Returning the promise - - -# Converting the Promise Chain to Async/Await - -To perform this conversion, we used the Codegen `convert_to_async_await()` api. - - -Learn more about the the usage of this api in the following [tutorial](/tutorials/promise-to-async-await) - - -## Step 1: Finding Promise Chains - -Extract all promise chains using the `TSFunction.promise_chains` method. - -```python -operation_promise_chains = [] -unique_files = set() - -# loop through all classes -for _class in codebase.classes: - - # loop through all methods - for method in _class.methods: - - # Skip certain methods - if method.name in ["each", "setPromiseCallback"]: - continue - - # Only process methods with operationPromise - if not method.find("operationPromise"): - continue - - # Collect all promise chains - for promise_chain in method.promise_chains: - operation_promise_chains.append({ - "function_name": method.name, - "promise_chain": promise_chain, - "promise_statement": promise_chain.parent_statement - }) - unique_files.add(method.file.filepath) - -print(f"Found {len(operation_promise_chains)} Promise chains") -print(f"Across {len(unique_files)} files") -``` - -```bash -Found 592 Promise chains -Across 393 files -``` - - -## Step 2: Converting to Async/Await - -Then we converted each chain and added proper error handling with try/catch: - -```python -for chain_info in operation_promise_chains: - promise_chain = chain_info["promise_chain"] - promise_statement = chain_info["promise_statement"] - - # Convert the chain - async_code = promise_chain.convert_to_async_await( - assignment_variable_name="operation" - ) - - # Add try-catch with callback handling - new_code = f""" - try {{ - {async_code} - if (callback) {{ - callback(null, operation); - }} - return operation; - }} catch(err: any) {{ - if (callback) {{ - callback(err); - }} - throw err; - }} - """ - promise_statement.edit(new_code) - - # Clean up old statements - statements = promise_statement.parent.get_statements() - return_stmt = next((stmt for stmt in statements - if stmt.statement_type == StatementType.RETURN_STATEMENT), None) - assign_stmt = next((stmt for stmt in reversed(statements) - if stmt.statement_type == StatementType.ASSIGNMENT), None) - - if return_stmt: - return_stmt.remove() - if assign_stmt: - assign_stmt.remove() -``` - -## The Conversion - -- Converted 592 Promise chains across the codebase -- Eliminated the need for `setPromiseCallback` utility -- Maintained backward compatibility with callback-style APIs -- Improved code readability and maintainability - - - - - - - - - - - -## Conclusion - -Promise chains using `.then()` syntax often leads to complex and deeply nested code that's harder to maintain. It's an active problem that many teams *want* to pursue but never end up doing so due to the time consuming nature of the migration. -Codegen can significantly accelerate these migrations by automating the conversion for several different cases. - -Want to try this yourself? Check out our [Promise to Async/Await tutorial](/tutorials/promise-to-async-await) \ No newline at end of file diff --git a/docs/blog/static-analysis-ai.mdx b/docs/blog/static-analysis-ai.mdx deleted file mode 100644 index a9988e6d2..000000000 --- a/docs/blog/static-analysis-ai.mdx +++ /dev/null @@ -1,67 +0,0 @@ ---- -title: "Static Analysis in the Age of AI Coding Assistants" -description: "Why traditional language servers aren't enough for the future of AI-powered code manipulation" -icon: "magnifying-glass-chart" -iconType: "solid" ---- - -As AI coding assistants like Cursor, Devin, and others become increasingly sophisticated, a common question emerges: "Why don't these tools leverage more sophisticated static analysis?" The answer reveals an important insight about the future of AI-powered code manipulation. - -## The Current Landscape - -Today's AI coding assistants typically implement static analysis in a limited way: - -- **Context Retrieval**: Tools like Cursor use graph-based queries to fetch relevant code context -- **Basic Refactoring**: Most rely on VSCode's built-in language server for operations like "rename symbol" -- **Text-Based Manipulation**: Changes are often made through direct text edits rather than semantic operations - -This approach works for simple, single-file changes. However, it breaks down when dealing with large-scale code transformations that require deep understanding of code relationships and dependencies. - -## The Challenge of Scale - -Why don't AI assistants just use existing language servers? The reality is that traditional language server protocols, while excellent for IDE features, have limitations when it comes to bulk code modifications: - -1. **Performance**: Processing large-scale changes through standard language servers is inherently slow -2. **Scope**: Traditional tools focus on file-level operations, not codebase-wide transformations -3. **Complexity**: Real-world refactors often require understanding complex relationships between code elements - -## The Rise of Codemod Frameworks - -Tools like `ts-morph`, `jscodeshift`, and others have emerged to fill this gap, offering more powerful code manipulation capabilities. However, they too have limitations: - -- Complex APIs that don't match how developers think about code changes -- Limited cross-language support -- Insufficient tooling for managing large-scale transformations -- Lack of integration with modern AI workflows - -## The Future: Agent-Native Language Servers - -The next evolution in this space is what we call "agent-native language servers" - tools built specifically for AI agents to manipulate code programmatically. These tools need to: - -1. **Express Changes as Code**: Enable AI agents to write programs that perform code transformations, rather than generating text patches -2. **Provide Rich Static Analysis**: Offer deep understanding of code relationships, dependencies, and impact analysis -3. **Scale Effectively**: Handle large-scale transformations across massive codebases -4. **Support the Full Lifecycle**: Address aspects beyond just code changes: - - Visualization of change impact - - PR management and code ownership - - Edge case detection and debugging - - Regression monitoring and notification - -## Beyond Simple Edits - -The future of AI-powered code manipulation isn't just about making text changes - it's about enabling AI agents to: - -1. **Build Their Own Tools**: Create and maintain their own transformation utilities -2. **Understand Impact**: Analyze the full implications of code changes -3. **Manage Complexity**: Handle cross-file, cross-language transformations -4. **Ensure Reliability**: Maintain correctness across large-scale changes - -## The Path Forward - -As companies like Grit.io and Codemod.com demonstrate, there's growing recognition that the future of AI-powered code transformation requires sophisticated static analysis. But more importantly, it requires tools that are built for how AI agents actually work - through code itself. - -The most powerful AI coding assistants won't just generate patches or suggest edits. They'll write programs that transform code, leveraging rich static analysis to ensure changes are correct, scalable, and maintainable. - -This is why we're building Codegen as a programmatic interface for code manipulation - not just another language server, but a foundation for AI agents to express complex code transformations through code itself. - -The future of code manipulation isn't just about better language models - it's about giving those models the right tools to act effectively on code. Just as self-driving cars need sophisticated controls to navigate the physical world, AI coding agents need powerful, precise interfaces to manipulate codebases. diff --git a/docs/changelog/changelog.mdx b/docs/changelog/changelog.mdx deleted file mode 100644 index 443e43046..000000000 --- a/docs/changelog/changelog.mdx +++ /dev/null @@ -1,1369 +0,0 @@ ---- -title: "Codegen Updates" -icon: "clock" -iconType: "solid" ---- - - -### [Removed GitHub requirement and made 'pink' optional.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.55.1) -- Removed GitHub as a requirement -- Made 'pink' an optional dependency - - - -### [adds setup_commands option and fixes macOS build failures.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.55.0) -- Add setup_commands configuration option -- Fix macOS wheel build failures - - - -### [Fixes API client installation and updates documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.54.4) -- Fix API client installation -- Revamp documentation with new pages and updates - - - - -### [Updates sentry-sdk and adds integration documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.54.3) -- Update sentry-sdk to v2.26.1 -- Add documentation pages on integrations - - - - -### [Improves stability and enhances documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.54.2) -- Upgrade sentry-sdk dependency to improve stability -- Enhance documentation with prioritized agent information - - - -### [Fixes undefined field type bug](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.54.1) -- Fix undefined field type bug - - - -### [Introduces new API client feature](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.54.0) -- Add API client feature - - - -### [Improves logger stream allocation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.53.0) -- Improve logger stream allocation - - - -### [Updates dependency sentry-sdk.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.31) -- Update dependency sentry-sdk to v2.25.1 - - - -### [Improves debugging with git init failure logs.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.30) -- Add logs for git initialization failure - - - -### [Fixes codebase initialization issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.29) -- Fix issue with codebase initialization - - - -### [Updates OpenAI dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.28) -- Update OpenAI dependency to v1.70.0 - - - -### [Upgrade sentry-sdk dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.27) -- Upgrade sentry-sdk dependency for better bug tracking - - - -### [Updates openai dependency to the latest version.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.26) -- Update dependency openai to version 1.69.0 - - - -### [remove unnecessary transaction in build_graph.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.25) -- Remove build_graph transaction - - - -### [Documentation update for `codegen create` command.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.24) -- Update documentation for `codegen create` command - - - - -### [Fixes missing module issue in CLI commands.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.23) -- Fix issue with missing module in CLI commands - - - - -### [Fixes issue retrieval in repository client.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.22) -- Fix issue retrieval in repository client - - - -### [Improves stability with sentry-sdk update.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.21) -- Update sentry-sdk to improve stability - - - -### [Removed legacy agent components.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.20) -- Remove legacy agent components - - - -### [Dependency update for OpenAI.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.19) -- Update OpenAI dependency to version 1.68.2 - - - -### [Updates sentry-sdk dependency and changelog.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.18) -- Update sentry-sdk dependency to v2.24.0 -- Update changelog - - - -### [Reverts API change, fixes duplication, updates docs.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.17) -- Revert changes to API for removing unused symbols -- Fix issue with duplicate additional tools -- Update API reference documentation - - - - -### [Updates OpenAI dependency and PR branch handling.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.16) -- Update dependency to OpenAI v1.68.0 -- Return branch name with PR changes - - - -### [fixes token limit inversion bug.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.15) -- Fix token limit inversion bug - - - -### [Fixes a maximum observation length error.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.14) -- Fix maximum observation length error - - - - -### [Fixes summarization error for images.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.13) -- Fix summarization error for images - - - -### [Renames search functionality](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.12) -- Renamed search functionality to ripgrep - - - -### [Fixes error, updates docs, adds TypeScript feature.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.11) -- Fix LLM truncation error -- Update API reference documentation -- Implement Namespace as TypeScript graph node - - - -### [Fixes collection script permissions and newline bug.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.10) -- Fix permissions on collection script -- Workaround for replace not adding newlines - - - - -### [Reintroduced schema for tool outputs.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.9) -- Re-add schema for tool outputs - - - -### [Update OpenAI dependency to improve stability.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.8) -- Update OpenAI dependency to v1.66.5 - - - -### [Improved documentation and fixed log issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.7) -- Updated API reference documentation -- Fixed logging for empty repositories and codebase parsing - - - -### [Fixes commit attribution issue](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.6) -- Fix commit attribution issue with codegen-sh - - - -### [Tool update to include default parameter values.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.5) -- Update tool to include default parameter values - - - - -### [Fixes parameter reference bug.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.4) -- Fixed parameter reference bug - - - - -### [enhances search by filename tool with pagination.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.3) -- Update search by filename tool to support pagination - - - - -### [Enhances agent and tools, increases token limit.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.2) -- Increased view file size limit for better usability -- Enhanced agent functionality to accept image URLs -- Fixed multiple broken links -- Increased output token limit for better performance -- Introduced schemas for tool outputs - - - -### [Fixes an error in the search files by name tool.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.1) -- Fix error in search files by name tool - - - - -### [New co-author extraction and developer tools](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.52.0) -- Extract co-author information from git configurations -- Introduce a global find/replace tool -- Add a file-finding tool - - - -### [Updates sentry-sdk and adds instance ID option.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.51.4) -- Update dependency sentry-sdk -- Add option to run multiple instance IDs by name - - - -### [Documentation enhancements and dependency update](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.51.3) -- Update sentry-sdk dependency -- Add integrations page to documentation -- Fix broken links in documentation - - - - -### [Introduces logger interface support.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.51.2) -- Add logger interface support - - - -### [Adds memory truncation feature and directory listing fix.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.51.1) -- Fix inefficient directory listing implementation. -- Introduce memory truncation feature for conversation history. -- Enhance conditionals handling and quality of life improvements. -- Improve analytics documentation and add CLI-based run example. - - - -### [Introduces Pink in codegen with updated API docs.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.51.0) -- Updated API reference documentation -- Implemented Pink in code generation - - - -### [Fixes draft setting for private repositories.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.50.2) -- Fix issue with draft setting for private repositories - - - -### [Fixes Relace Edit Tool URL issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.50.1) -- Fix Relace Edit Tool URL - - - -### [Removes JWT authentication feature.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.50.0) -- Remove JWT authentication feature - - - - -### [Enhancements to error handling and file validation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.6) -- Improved error handling for file not found errors in RelaceEditTool -- Added file validity and existence checks to create_file -- Updated API reference - - - -### [Fixes IndexError and file parse issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.5) -- Fix IndexError when message.content is empty -- Resolve issue with disable_file_parse for create_file - - - -### [Increased maximum token limit.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.4) -- Increased maximum token limit - - - - -### [Documentation updates and AI dashboard implementation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.3) -- Updated API reference documentation -- Fixed tests patch -- Cleaned up symbol attributions example -- Implemented AI impact dashboard -- Fixed attribution tutorial - - - -### [Updates dependencies and fixes assignment issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.2) -- Update OpenAI dependency to v1.66.3 -- Add JWT as an explicit dependency -- Improve error handling mechanisms -- Fix issues with assignment functionality - - - -### [API and bug fixes for import resolution and file handling.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.1) -- Updated API reference documentation -- Fixed import resolution issues -- Ensured correct file directory handling - - - - -### [Tool enhancements and compatibility fixes](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.49.0) -- Enhance tool functionality -- Fix from_repo compatibility with latest conventions -- Add demo for codebase statistics -- Update API reference documentation - - - -### [File tool improvements and dependency update](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.9) -- Update dependency openai to v1.66.1 -- Improve create file tool functionality - - - -### [Enhancements in documentation and repository retrieval.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.8) -- Bug fix: updated openai dependency to v1.66.0 -- Added architecture documentation -- Enhanced API reference documentation -- Introduced full history option in repository retrieval - - - - -### [Enhances error handling and adds custom langgraph nodes.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.7) -- Improved error handling with enhanced retry policy -- Introduced custom langgraph nodes - - - -### [Fixes null body issue in pull request context.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.6) -- Fix null body issue in pull request context - - - -### [Adds dataset subsets and improves CLI arguments.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.5) -- Updated OpenAI dependency -- Improved command line arguments -- Added subsets of swe-bench lite dataset - - - -### [Fixes import issue and removes outdated Chat Agent.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.4) -- Fix search tool import issue -- Remove obsolete Chat Agent implementation - - - -### [Fixes git token issue and integrates xAI provider.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.3) -- Fix issue with remote git repo token requirement -- Integrate new xAI provider -- Update and expand API documentation - - - -### [Fixes PR viewing issue returning 404 error.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.2) -- Fix issue with viewing PR returning 404 - - - -### [Fixes and documentation update with langsmith tagging.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.1) -- Updated API reference -- Fixed issue with Codebase.from_repo -- Enabled model name tagging for langsmith traces - - - -### [adds view PR checks tool.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.48.0) -- Add view PR checks tool - - - -### [Adds GitHub issues search tool and eval command update.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.47.0) -- Adds a new tool for searching GitHub issues -- Makes model a parameter for the run eval command - - - -### [Bug fixes and GitHub Webhook functionality improvements.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.46.1) -- Fix invalid file handling bug -- Improve GitHub Webhook functionality -- Enhance testing and documentation updates - - - -### [Introduces a better search tool and dynamic scaling.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.46.0) -- Fix issues with unpacking functionality -- Implement dynamic scaling for asyncio requests -- Introduce a better search tool -- Enable evaluator to run on existing predictions - - - -### [Improved bug fixes with updated dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.45.1) -- Update dependency to improve bug fixes - - - -### [Improve performance and update documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.45.0) -- Add runner tooling feature -- Speed up directory tree generation -- Remove unnecessary tools from agent implementation -- Update API reference and fix documentation links - - - -### [Fixes a Slack schema error.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.44.4) -- Fix Slack schema error - - - -### [Fixes Slack event type handling for rich text.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.44.3) -- Fix Slack event type handling for rich text - - - -### [Fixes and improvements to event handling and codebase.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.44.2) -- Fix Slack event handling with thread-ts addition -- Resolve codebase corruption in file editing -- Improve pypath resolution for __init__ files -- Update API reference documentation - - - -### [Fixes Slack integration and agent-related issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.44.1) -- Fix Slack integration and minor agent issues - - - -### [adds URL replacement feature.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.44.0) -- Add feature for replacing URLs - - - -### [Bug fixes and documentation link corrections.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.43.3) -- Fix Slack integration callback -- Remove sandbox runner reset feature -- Correct broken links in blog posts - - - -### [Documentation updates and bug fix](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.43.2) -- Updated API reference documentation -- Fixed codeowners property and added regression unit tests - - - -### [Improves test time, evaluation, and documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.43.1) -- Improved test time by modifying validation flow -- Enhanced evaluation with new dataset options -- Extracted and refactored utility functions for better code organization -- Added installation instructions for Windows/WSL -- Updated API reference documentation - - - -### [Add LLM tracing link feature for LangSmith](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.43.0) -- Add LLM tracing link feature for LangSmith - - - -### [Fixes compatibility issue by pinning codegen version.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.42.2) -- Pin codegen version to address compatibility issues - - - - -### [Documentation updates and unified file import methods.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.42.1) -- Updated and consolidated API documentation -- Unified file import methods for improved usability - - - -### [Enhances local state sync and import parsing.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.42.0) -- Sync changes to local state before execution -- Updated API reference documentation -- Improved import parsing in the parser - - - -### [Dependency update and improved documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.8) -- Update OpenAI dependency to v1.65.1 -- Convert function names to use underscores -- Updated API reference documentation - - - -### [Fixes parameter handling in container management.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.7) -- Remove extra parameter from container handler - - - -### [update OpenAI dependency to v1.65.0.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.6) -- Update dependency to OpenAI v1.65.0 - - - -### [Fix log error issue when commit_sha is None.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.5) -- Fix log error when commit_sha is None - - - -### [Improves Dockerfile support for various versions.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.4) -- Improve Dockerfile support for published and dev versions - - - -### [Fixes and documentation improvements.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.3) -- Fix Dockerfile-runner inclusion in codegen package -- Update language detection testing parameters -- Add troubleshooting section to documentation - - - - -### [Fixes and improvements for codemods and daemon.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.2) -- Fix issue with nested __pycache__ directory in codemods -- Improve git configuration and daemon functionality - - - -### [fixes a bug and adds new Codebase support methods.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.1) -- Fix determine programming language bug -- Support Codebase.from_string and Codebase.from_files -- Updated API reference - - - -### [adds --daemon option and improves dataset access.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.41.0) -- Add --daemon option to codegen run command -- Improve swebench dataset access - - - -### [Adds Chat Agent and subdirectory support in codegen.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.40.0) -- Add functionality to specify subdirectories in `codegen.function` -- Introduce a new Chat Agent - - - -### [Custom codebase path setting for code generation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.39.1) -- Allow setting custom codebase path in code generation - - - -### [Lazy Graph Compute Mode and new agent run snapshots.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.39.0) -- Implement Lazy Graph Compute Mode -- Add agent run snapshots feature -- Update API reference documentation - - - -### [Adds ripgrep search tool and updates API docs.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.38.0) -- Integrate ripgrep in search tool -- Update API reference documentation - - - - -### [Fixes linting issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.37.1) -- Fix linting issues - - - - -### [Custom package resolving and error handling improvements.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.37.0) -- Allow custom overrides for package resolving -- Add optional sys.path support -- Improve error handling with linear tools -- Fix wildcard resolution issues - - - - -### [File Parse Mode disabled by default](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.36.0) -- Disable File Parse Mode feature implemented - - - - -### [Replaces edit tool and enhances test configurations.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.35.0) -- Replace edit tool with a new version -- Enhance test configurations and execution - - - - -### [Introduces Docker client and major refactor.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.34.0) -- Introduce Docker client feature -- Refactor codebase directory structure -- Implement heuristics-based minified file detection - - - - -### [Improves GitHub Actions handling and fixes Docker issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.33.1) -- Improve GitHub Actions token and repo handling -- Fix codegen Docker runner issues -- Update agent documentation - - - -### [Introduces CodegenApp and enhances codegen capabilities.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.33.0) -- Introduce CodegenApp feature -- Add local codegen server daemon -- Implement minified file detection using heuristics - - - - -### [Improves compatibility with updated dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.32.2) -- Update dependency for better compatibility - - - - -### [Restores default setting for RepoOperator.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.32.1) -- Restore default setting for RepoOperator to bot_commit=False - - - - -### [Langgraph migration and improved dependency instructions.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.32.0) -- Improved dependency installation instructions -- Migrated to Langgraph with Multi-LLM Config -- Ignored compiled and minified JavaScript files - - - - -### [Fixes GitHub token environment variable key issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.31.1) -- Remove secrets_ prefix from GitHub token environment variable key - - - - -### [Completes tool upgrades](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.31.0) -- Implement final set of upgrades for tools - - - - -### [GitHub action updated and PyGitHub dependency fixed.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.30.1) -- Update GitHub action setup to version 5.3 -- Fix dependency issue with PyGitHub update to version 2.6.1 - - - - -### [Implements tooling fixes.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.30.0) -- Implement tooling fixes - - - - -### [introduces benchmarking harness and refactors configuration.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.29.0) -- Introduce a benchmarking harness for SWE -- Refactor configuration into a dedicated module - - - - -### [Improves security by removing secrets prefix.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.28.1) -- Remove secrets prefix and global .env file. - - - - -### [Enhances the codebase agent with additional tools.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.28.0) -- Add extra tools to the codebase agent - - - - -### [Improved configuration management and documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.27.0) -- Simplify configuration by using a .env file with autoload -- Enhance code agent documentation -- Add example of using codegen SDK to build integration bots - - - - -### [Enhance opt out filter handling.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.26.3) -- Introduce should_handle callback for opt out filters - - - - -### [Fixes UnicodeDecodeError and enhances file import controls.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.26.2) -- Fix UnicodeDecodeError when instantiating codebase from repo -- Add node_modules to global file ignore list -- Ensure files are not imported directly outside specified folder - - - - -### [Token requirement relaxed and unpacking feature removed.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.26.1) -- Relax GitHub token requirement on initialization -- Remove unpacking assignment feature - - - - -### [introduces paginated view file tool.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.26.0) -- Introduce paginated view file tool - - - - -### [Fixes semantic edit tool issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.25.2) -- Fix semantic edit tool issues - - - - -### [Improves tool output rendering.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.25.1) -- Improve tool output rendering - - - - -### [Adds top-level code agent and unicode parsing fix.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.25.0) -- Introduce top-level code agent feature -- Fix unicode filename parsing in codebase - - - - -### [Fixes filesystem corruption and improves tool observations.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.24.1) -- Upgrade tool observation dataclasses -- Fix local filesystem corruption in `get_codebase_session` -- Re-enable and fix `verify_output` logic - - - - -### [Introduces new RunCodemodTool feature.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.24.0) -- Introduce RunCodemodTool feature - - - - -### [Adds replace tool and supports basic file operations.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.23.0) -- Add codebase language replace tool -- Allow basic file operations for non-supported languages - - - - -### [resolves issues by removing MultiAIProvider.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.22.4) -- Remove MultiAIProvider to resolve associated issues - - - - -### [Introduces a linear webhook example.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.22.3) -- Add linear webhook example - - - - -### [Enhancements and bug fixes for semantic editing.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.22.2) -- Unified operators for consistent behavior -- Improved import handling for File/Symbol Index -- Enhanced semantic edit functionality with line-specific control -- Bug fix: Display line numbers in semantic edit -- Updated agent documentation - - - - -### [Fixes async bug by removing unnecessary reset call.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.22.1) -- Fix async bug by removing codebase reset call - - - - -### [introduces new client feature and language detection.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.22.0) -- Add server client vs. codebase client feature -- Implement git-based codebase language detection - - - - -### [Enhances promise handling and updates documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.21.2) -- Implemented TSPromise class for better promise handling -- Fixed default types setting -- Updated external links and documentation - - - - -### [Adds initial server and fixes codebase parsing.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.21.1) -- Add initial server with run and codebase initialization -- Fix non-blocking codebase parsing issue - - - - -### [Refactor of vector index](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.21.0) -- Refactor vector index for improved functionality - - - - -### [Update OpenAI dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.20.2) -- Update OpenAI dependency to v1.63.2 - - - - -### [Dependency updates for sentry-sdk and openai.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.20.1) -- Update sentry-sdk dependency to v2.22.0 -- Update openai dependency to v1.63.1 - - - - -### [Introduces a new agent CLI.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.20.0) -- Introduce new agent CLI - - - - -### [Bug fix for GitHub type handling.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.19.1) -- Bug fix for GitHub type handling - - - - -### [Enable GitHub webhooks and fix tutorial links.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.19.0) -- Enable GitHub webhooks for better integration -- Fix links to examples in tutorials -- Apply agent documentation hotfixes - - - - -### [Introduces Slack webhook handler and improves documentation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.18.0) -- Add Slack webhook handler feature -- Improve documentation for research agent - - - - -### [Bug fix and new Codebase Analytics Dashboard tutorial](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.17.2) -- Fixes deep code research bug -- Adds Codebase Analytics Dashboard tutorial - - - - -### [Bug fix with pygithub dependency update.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.17.1) -- Update dependency pygithub to v2.6.0 for improved stability - - - - -### [Introduces BashCommandTool and improves tool arrangement.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.17.0) -- Introduce BashCommandTool feature -- Improve tools arrangement - - - - -### [Introduces search_linear and create_linear tools.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.16.0) -- Introduce search_linear tool -- Introduce create_linear tool - - - - -### [Adds linear tools and improves import resolution.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.15.0) -- Add linear tools feature -- Fix documentation initialization issue -- Improve import wildcard resolution - - - - -### [Enhanced ergonomic web hook registration](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.5) -- Enhanced web hook registration for improved ergonomics - - - - -### [Adds .json directories support and fixes a bug.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.4) -- Support for directories with .json files -- Fix unauthenticated create bug -- Documentation improvements - - - - -### [Fixes branch creation issue in create-pr tool.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.3) -- Fix bug in branch creation for the create-pr tool - - - - -### [fixes an import bug.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.2) -- Fix import bug - - - - -### [LSP is now an optional dependency.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.1) -- Make LSP an optional dependency - - - - -### [Add LSP and term migration for codegen functionality.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.14.0) -- Add code generation language server protocol -- Migrate terminology from 'programming_language' to 'language' -- Improve and update documentation - - - - -### [improves link annotation and config commands.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.13.1) -- Support for directories in link annotation -- Add --global flag support in config commands -- Enhance repository operator with GitHub property - - - - -### [Adds link highlighting and LSP progress reporting.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.13.0) -- Add message highlighting for links -- Implement LSP progress reporting - - - - -### [Removes cache warm-up for improved performance.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.12.3) -- Removed cache warm-up - - - - -### [Fixes tool arrangement issues.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.12.2) -- Fix tool arrangement issues - - - - -### [Fixes list directory tool bugs](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.12.1) -- Fix list directory tool bugs - - - - -### [Session validation enhancement.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.12.0) -- Session validation added on creation and retrieval - - - - -### [Fixes PR tool checkout issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.11.4) -- Fix PR tool checkout issue on custom branches - - - - -### [Fixes tool handling and improves directory tests.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.11.3) -- Fix tools handling when files are not found -- Improve directory tests - - - - -### [Fixes and enhancements for PR process and GitHub token usage.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.11.2) -- Fix CodebaseGraph rename issue -- Enhance GitHub token usage -- Improve pull request creation process - - - - -### [Adds Neo4j extension and fixes config tests.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.11.1) -- Add Neo4j extension for codebase graph export -- Fix config tests -- Refactor and break up config models - - - - -### [Global session management and decoupled auth.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.11.0) -- Implement global session management -- Decouple authentication module - - - - -### [add documentation indexing instructions.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.10.4) -- Add documentation indexing instructions - - - - -### [Fixes init command and adds create PR tool.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.10.3) -- Fix issue with init command -- Add create PR tool for contributors - - - - -### [Fixes import path and adds MCP examples.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.10.2) -- Fixed import path issue -- Added additional MCP examples - - - - -### [Fixes a tool issue and enhances code maintainability.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.10.1) -- Fix issue with view_file tool content -- Deduplicate codebase for improved maintainability - - - - -### [Support for reading local git repo config.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.10.0) -- Read repository configuration from local git instance - - - - -### [fixes a function call issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.9.2) -- Fix function call issue - - - - -### [Enhancements to agent implementation.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.9.1) -- Improve agent implementation - - - - -### [Introducing Codegen-lsp v0 with additional test coverage.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.9.0) -- Introduce Codegen-lsp v0 feature -- Add tests for codebase.create_pr - - - - -### [Introduces codeowners interface and enhances codegen.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.8.0) -- Update code generation command -- Introduce new codeowners interface -- Add new examples and improve documentation -- Support for creating pull requests - - - - -### [Fixes Slack bot action release-tag input issue.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.6.4) -- Fix issue with Slack bot action regarding release-tag input - - - - -### [Fixes git tagging and adds a Slack bot example.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.6.3) -- Fix git tagging method for improved accuracy -- Add Slack bot example - - - - -### [Structural refactor, clearer naming, and new permissions](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.6.2) -- Add content write permission -- Refactor file IO for better structure -- Rename `CodebaseGraph` to `CodebaseContext` for clarity -- Unified dependency management - - - - -### [Introduces VectorIndex and supports x86_64 mac.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.6.1) -- Add VectorIndex extension and new MCP server feature. -- Update Plotly requirement and integrate Plotly.js 3.0.0. -- Fix various bugs and improve parsing tests. -- Enhance documentation with new tutorials and examples. -- Support added for x86_64 mac architecture. - - - - -### [Changes default URLs and removes access token.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.30) -- Change default URLs -- Remove access token from local repo operator - - - - -### [Fixes the GithubClient constructor.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.29) -- Fix GithubClient constructor - - - - -### [Fixes performance issues by disabling uv cache.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.28) -- Disable uv cache to resolve performance issues - - - - -### [Enhancements and bug fixes including asyncify fix.](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.27) -- Fix asyncify return type bug -- Add foundations for PR bot static analysis -- Generate changelog -- Remove default og:image setting - - - -### [Simplified Slack notifications](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.26) -- Simplified Slack notifications by removing description field - - - - -### [JSX parsing improvements and workflow optimizations](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.25) -- Fixed JSX prop parsing mechanism -- Added semantic release workflow improvements -- Fixed handling of empty collections -- Added performance optimizations with Mypyc/Cython -- Improved CI/CD pipeline configuration - - - - -### [Adds Python 3.13 and ARM64 support with feature improvements](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.24) -- Added support for Python 3.13 and ARM64 architecture builds -- Added documentation for incremental recomputation -- Introduced feature flag for generics support -- Fixed issues with duplicate edge creation -- Improved pre-commit hook functionality and stability - - - - -### [Adds symbol flags and improves debugging capabilities](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.23) -- Added new symbol flag functionality for Python and TypeScript -- Introduced duplicate dependencies strategy for file movement -- Enhanced debugging capabilities and server health monitoring -- Improved documentation with new guides and usage examples -- Fixed various issues with codemod file creation and sandbox server - - - - -### [Improves testing and fixes release-related issues](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.22) -- Fixed changelog generation and wheel release issues -- Improved test suite with timeouts and standardized move_to_file tests -- Enhanced CI/CD pipeline configuration - - - - -### [Adds ephemeral server and improves documentation](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.21) -- Added ephemeral server functionality -- Improved documentation generation with better type resolution and class docstrings -- Enhanced CI/CD workflows and testing infrastructure - - - - -### [ARM support for Linux](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.19) -- Added ARM support for Linux platforms -- Enhanced documentation with architecture docs and improved docstrings -- Updated OpenAI dependency to version 1.61.0 - - - - -### [Adds system prompt generation and improves core functionality](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.18) -- Added automatic system prompt generation and gist client integration -- Restored namespace module support functionality -- Removed dynamic widget component from home page -- Fixed parse error handling -- Enhanced documentation and workflow improvements - - - - -### [Platform and file handling improvements](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.17) -- Enhanced file handling with improved TSourceFile return type -- Updated platform support capabilities -- Added community resources for contributors - - - - -### [Pydantic v2 migration and documentation updates](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.16) -- Update to Pydantic v2 imports and config handling -- Documentation and example improvements -- Configuration file updates - - - - -### [Removes auth requirement and fixes path handling](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.15) -- Remove authentication requirement for create command -- Fix path handling and directory creation -- Resolve validator import issues - - - - -### [Validation system improvements](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.14) -- Updated validation system to use BeforeValidator instead of PlainValidator - - - - -### [Updates to Pydantic v2 and documentation improvements](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.13) -- Updated to Pydantic v2 for span handling -- Added documentation for import loops -- Improved IDE installation instructions - - - - -### [Documentation improvements and module resolution fixes](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.12) -- Enhanced documentation with improved visualization linking and codebase examples -- Fixed module resolution issues -- Updated VSCode installation guide with Python extensions -- Improved documentation metadata and thumbnail images - - - - -### [Adds graph disabling feature and fixes command handling](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.11) -- Add disable_graph feature flag to reduce memory usage and parsing time -- Fix bug in create command response handling - - - - -### [Adds language detection and improves file handling](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.10) -- Added package.json-based repository language detection -- Improved file editing capabilities with new raw text edit features -- Enhanced documentation with function decorator guide and codebase visualization tutorial -- Fixed GitHub 404 error handling -- Added type fixes for codebase initialization - - - - -### [Documentation improvements and dynamic import support](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.9) -- Improved documentation with new guides and clarifications on file types -- Added support for dynamic import detection -- Added reset command to CLI -- Improved integration tests for better contributor experience -- Fixed widget URLs and various documentation improvements - - - - -### [Fixes branch sync and improves documentation](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.8) -- Fix branch synchronization clone URL issue -- Enhance documentation guides -- Update development dependencies - - - - -### [Improves runner functionality and build process](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.7) -- Enhanced runner module functionality and synchronization -- Added automatic function imports generation during build process -- Updated documentation and README - - - - -### [New codebase initialization workflow and analytics integration](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.6) -- Introduced new codebase initialization workflow -- Added PostHog integration and override functionality -- Enhanced documentation for session options -- Improved sandbox runner synchronization - - - - -### [Adds create flag and improves Git repository handling](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.5) -- Added `-d` flag to `codegen create` command -- Fixed Gradio integration issues -- Improved automatic base path detection for Git repositories -- Enhanced codebase reset functionality to only affect SDK changes -- Updated documentation and README - - - - -### [Adds venv management and TypeScript export support](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.4) -- Added virtual environment creation and persistence for `codegen init` -- Added support for codebase exports in TypeScript projects -- Reorganized test structure for better maintainability -- Updated graph widget configuration and URLs - - - - -### [Graph widget and system prompt features added](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.3) -- Added graph widget visualization feature -- Enhanced documentation with improved readability and new guides -- Added system prompt functionality -- Fixed core commands: codegen run and create -- Various internal code cleanup and reorganization - - - - -### [Adds notebook functionality and improves documentation](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.2) -- Added new codegen notebook functionality -- Fixed several documentation rendering issues and broken links -- Added function call parameter documentation helpers -- Fixed various type annotations and AST-related bugs -- Added README files for codegen modules - - - - -### [Adds remote codebase support and improves documentation](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.1) -- Added support for fetching remote codebases -- Fixed documentation and GitHub link parsing issues -- Improved test organization and coverage -- Added missing documentation pages -- Resolved repository configuration issues - - - - -### [Major documentation overhaul and API improvements](https://github.com/codegen-sh/codegen-sdk/releases/tag/v0.5.0) -- New documentation system with MDX support and interactive codemod widget -- Simplified API with improved module organization and naming -- Added Codebase and CLI functionality for easier code manipulation -- Introduced fetch_codebase feature for remote repository handling -- Enhanced documentation with new guides and examples -