Document top similar repositories to Forky#19
Conversation
Reviewer's GuideReplaces the placeholder README with a structured similarity-analysis template for identifying top GitHub repositories related to Forky and adds a captured GitHub Search API results file similar_repos.json to back the analysis data. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request formalizes the documentation of repositories similar to Forky. It establishes a structured report within Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. Footnotes
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - I've left some high level feedback:
- The new README still looks like an internal prompt/template (with
<purpose>,<instructions>,[[variables]], etc.); consider replacing it with a user-facing similarity report in normal Markdown that directly describes Forky and the ranked repos instead of the meta-instructions for generating that report. - If
similar_repos.jsoncontains the full raw GitHub API responses, you may want to trim it to only the fields actually used in the analysis (name, URL, description, topics, stars) or move it into a dedicateddata/oranalysis/directory to keep the repo root lean.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The new README still looks like an internal prompt/template (with `<purpose>`, `<instructions>`, `[[variables]]`, etc.); consider replacing it with a user-facing similarity report in normal Markdown that directly describes Forky and the ranked repos instead of the meta-instructions for generating that report.
- If `similar_repos.json` contains the full raw GitHub API responses, you may want to trim it to only the fields actually used in the analysis (name, URL, description, topics, stars) or move it into a dedicated `data/` or `analysis/` directory to keep the repo root lean.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates the repository's documentation by adding a similarity analysis of related projects. It introduces a new similar_repos.json file to store data from the GitHub API for reproducibility, which is a good practice. It also replaces the placeholder README.md with a template for generating the analysis report. While the intent is clear, I have a couple of suggestions. The main point of feedback is regarding the format of the README.md file, which is currently an XML-like template and not a human-readable Markdown document. I've also noted a minor formatting issue in the new JSON file. Please see my detailed comments.
| <purpose> | ||
| Provide a formal report that identifies the top 10 GitHub repositories most similar | ||
| to the Forky project (conversation branching, DAG-based chat management, and LLM | ||
| workflows), based solely on the user-supplied description and the GitHub search | ||
| results captured in the attachment data. | ||
| </purpose> | ||
|
|
||
| <context> | ||
| <role> | ||
| Documentation Analyst / Technical Revisor. | ||
| <tone>Formal, coherent, impersonal, and extensive.</tone> | ||
| <domain>Repository Similarity Analysis for LLM Tooling.</domain> | ||
| </role> | ||
|
|
||
| <input_handling> | ||
| Treat [[attachment_files]] as the textual data extracted from the GitHub API | ||
| search responses stored locally for this task. | ||
| </input_handling> | ||
|
|
||
| <constraints> | ||
| <constraint type="critical">TOTAL SANITIZATION: No identifiers or factual | ||
| statements from the template may remain; all content is replaced with Forky | ||
| and similarity-search data.</constraint> | ||
| <constraint type="critical">INFERENCE ALLOWED: Similarity ordering is inferred | ||
| using repository descriptions, topics, and stated features.</constraint> | ||
| <constraint type="critical">CONFLICT RESOLUTION: If data sources conflict, both | ||
| values are recorded with source tags.</constraint> | ||
| <constraint type="formatting">PRESERVE STRUCTURE: Maintain the hierarchy, | ||
| section order, and list styles of the template where possible.</constraint> | ||
| </constraints> | ||
| </context> | ||
|
|
||
| <instructions> | ||
| <instruction step="1">STRUCTURAL MAPPING: Identify fixed sections and variable | ||
| fields within this document template.</instruction> | ||
|
|
||
| <instruction step="2">DATA EXTRACTION: | ||
| a. Extract the target repository purpose and features from [[new_raw_data]]. | ||
| b. Extract candidate repositories from [[attachment_files]].</instruction> | ||
|
|
||
| <instruction step="3">CONFLICT CHECK: Compare overlapping fields (e.g., | ||
| descriptions or topics) and capture discrepancies if found.</instruction> | ||
|
|
||
| <instruction step="4">DRAFTING & SUBSTITUTION: | ||
| a. Rebuild the document using this structure. | ||
| b. Replace all sections with Forky-specific task details and similarity results. | ||
| c. Provide a ranked list of 10 similar repositories with brief rationales.</instruction> | ||
|
|
||
| <instruction step="5">LIST HANDLING: | ||
| a. Use ordered lists for ranked repositories. | ||
| b. Include only repositories present in the attachment data. | ||
| c. Do not retain unused template items.</instruction> | ||
|
|
||
| <instruction step="6">GAP FILLING: If the raw data omits a field (e.g., | ||
| explicit similarity criteria), infer it based on standard repository analysis.</instruction> | ||
|
|
||
| <instruction step="7">DISCREPANCY REPORTING: If conflicts exist, add an | ||
| OBSERVATIONS section at the end and list both values with sources.</instruction> | ||
|
|
||
| <instruction step="8">ANTI-RESIDUE SCAN: Ensure no template-specific details | ||
| remain in the final output.</instruction> | ||
| </instructions> | ||
|
|
||
| <variables> | ||
| <variable name="[[task_request]]" required="true"> | ||
| <description>Identify the 10 GitHub repositories most similar to Forky.</description> | ||
| </variable> | ||
| <variable name="[[target_repo_url]]" required="true"> | ||
| <description>https://github.com/ishandhanani/forky</description> | ||
| </variable> | ||
| <variable name="[[similarity_criteria]]" required="true"> | ||
| <description> | ||
| Overlap in conversation branching, DAG or tree structures, multi-path chat | ||
| exploration, LLM-driven chat management, and graph visualization. | ||
| </description> | ||
| </variable> | ||
| <variable name="[[data_sources]]" required="true"> | ||
| <description> | ||
| User-provided Forky description (raw data) and GitHub Search API results | ||
| stored in similar_repos.json (attachment data). | ||
| </description> | ||
| </variable> | ||
| </variables> | ||
|
|
||
| <input_data> | ||
| <template_document><![CDATA[ | ||
| [[Template content fully replaced with Forky similarity analysis.]] | ||
| ]]></template_document> | ||
|
|
||
| <new_raw_data><![CDATA[ | ||
| Target repository: Forky (Git-style conversation management for LLMs). | ||
| Key concepts: conversation DAG, branching, checkout, semantic merge, | ||
| multi-provider LLM support, web/CLI interfaces, and graph visualization. | ||
| ]]></new_raw_data> | ||
|
|
||
| <attachment_files><![CDATA[ | ||
| Extracted GitHub Search API candidates from similar_repos.json, including | ||
| repository names, URLs, descriptions, topics, and star counts. | ||
| ]]></attachment_files> | ||
| </input_data> | ||
|
|
||
| <output_format_specification> | ||
| <format>Plain text or Markdown, strictly mirroring the layout of the template.</format> | ||
| <language>en_US</language> | ||
| </output_format_specification> | ||
|
|
||
| <examples> | ||
| <example> | ||
| <scenario>Top 10 Similar GitHub Repositories to Forky</scenario> | ||
| <output_fragment><![CDATA[ | ||
| 1) akivacp/chatgpt-json-tree-viewer | ||
| URL: https://github.com/akivacp/chatgpt-json-tree-viewer | ||
| Rationale: Visualizes branching conversation trees, aligning with Forky’s | ||
| graph-based chat history exploration. | ||
|
|
||
| 2) ivanbaluta/aistudio-chat-visualizer | ||
| URL: https://github.com/ivanbaluta/aistudio-chat-visualizer | ||
| Rationale: Interactive branching tree graph for chats, similar DAG | ||
| navigation focus. | ||
|
|
||
| 3) iterabloom/BranchyMcChatFace | ||
| URL: https://github.com/iterabloom/BranchyMcChatFace | ||
| Rationale: Explicit conversation branching with dialogue trees and | ||
| visualization. | ||
|
|
||
| 4) tldraw/branching-chat-template | ||
| URL: https://github.com/tldraw/branching-chat-template | ||
| Rationale: Visual branching conversation interface with AI integration. | ||
|
|
||
| 5) PaoloJN/ai-chat-tree | ||
| URL: https://github.com/PaoloJN/ai-chat-tree | ||
| Rationale: Hierarchical AI chat conversations with branching contexts. | ||
|
|
||
| 6) jamwalsudip/chatgpt-branching | ||
| URL: https://github.com/jamwalsudip/chatgpt-branching | ||
| Rationale: Branching conversation tree tracker for ChatGPT. | ||
|
|
||
| 7) Utsav-Ladani/Chat-Trees | ||
| URL: https://github.com/Utsav-Ladani/Chat-Trees | ||
| Rationale: Branching conversation tree app for AI chats. | ||
|
|
||
| 8) harriety/tree-chat | ||
| URL: https://github.com/harriety/tree-chat | ||
| Rationale: Tree-structured chat interface for multi-path reasoning. | ||
|
|
||
| 9) sbeeredd04/Aether | ||
| URL: https://github.com/sbeeredd04/Aether | ||
| Rationale: Chat multiverse with visual tree exploration and multi-model | ||
| support. | ||
|
|
||
| 10) Tiledesk/design-studio | ||
| URL: https://github.com/Tiledesk/design-studio | ||
| Rationale: Graph-based conversation designer with LLM/GPT focus. | ||
| ]]></output_fragment> | ||
| </example> | ||
| </examples> | ||
|
|
||
| <self_check> | ||
| <checklist> | ||
| <item>All content is derived from Forky’s description and GitHub search data.</item> | ||
| <item>Top 10 list contains only repositories present in attachment data.</item> | ||
| <item>Template-specific facts are fully removed.</item> | ||
| <item>No conflicts detected between raw and attachment data.</item> | ||
| </checklist> | ||
| </self_check> | ||
|
|
||
| <evaluation_notes> | ||
| <test_cases> | ||
| <case>Branching conversation visualization tools</case> | ||
| <case>Conversation tree or DAG management interfaces</case> | ||
| <case>LLM chat systems with graph-based navigation</case> | ||
| <case>Conversation designers using graph structures</case> | ||
| </test_cases> | ||
| <success_definition>Top 10 similar repositories are listed with URLs and | ||
| rationales aligned to Forky’s conversation DAG and branching model.</success_definition> | ||
| </evaluation_notes> | ||
|
|
||
| <documentation> | ||
| <usage> | ||
| <step>Use the provided Forky summary to define similarity criteria.</step> | ||
| <step>Review GitHub API candidates and rank the top 10 by feature overlap.</step> | ||
| <step>Publish a formal list with repository names, links, and rationales.</step> | ||
| </usage> | ||
| <known_limitations> | ||
| <limitation>Similarity is inferred from public descriptions and topics.</limitation> | ||
| <limitation>Search results reflect GitHub API ranking at query time.</limitation> | ||
| </known_limitations> | ||
| </documentation> |
There was a problem hiding this comment.
The content of this README.md file is structured as an XML-like template, likely for an LLM, rather than a human-readable Markdown document. A README.md file is the main entry point for a repository and should be easily readable when rendered on platforms like GitHub. The current format will display as raw text with tags, which is not ideal for documentation. Consider moving this template to a separate file (e.g., report_template.xml) and using README.md to present the final, rendered similarity analysis in standard Markdown format. The content within the <output_fragment> tag provides a good example of what the final README.md could contain.
| "topics": [] | ||
| } | ||
| ] | ||
| } No newline at end of file |
There was a problem hiding this comment.
This file is missing a final newline character. It is a common convention to end text files with a newline. This can prevent issues with certain tools and file processing operations (e.g., cat).
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
1 issue found across 2 files
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name="README.md">
<violation number="1" location="README.md:87">
P1: README content is still a generation template with placeholders, not the actual finalized top-10 similarity report.</violation>
</file>
Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.
|
|
||
| <input_data> | ||
| <template_document><![CDATA[ | ||
| [[Template content fully replaced with Forky similarity analysis.]] |
There was a problem hiding this comment.
P1: README content is still a generation template with placeholders, not the actual finalized top-10 similarity report.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At README.md, line 87:
<comment>README content is still a generation template with placeholders, not the actual finalized top-10 similarity report.</comment>
<file context>
@@ -1 +1,188 @@
+
+<input_data>
+ <template_document><![CDATA[
+ [[Template content fully replaced with Forky similarity analysis.]]
+ ]]></template_document>
+
</file context>
1 participant
Motivation
Description
README.mdwith a template-structured report that describes the similarity task, ranking criteria, and a ranked list of candidate repositories with rationales.similar_repos.jsoncontaining the captured GitHub Search API responses (repository names, URLs, descriptions, topics, and star counts) used as the attachment/data source for the analysis.similar_repos.jsonfor traceability.Testing
python - <<'PY' ...(GitHub search script) savedsimilar_repos.json,wc -l similar_repos.jsonreturned a non-zero line count, andsed -n '1,160p' similar_repos.jsondisplayed the expected JSON fragment.README.mdandsimilar_repos.jsonwere inspected withnl/sedand found to contain the intended report and captured search results.Codex Task
Summary by Sourcery
Document a structured similarity analysis for the Forky repository and persist the GitHub search data used to identify related projects.
Documentation:
Chores:
Summary by cubic
Adds a structured similarity report to
README.mdthat ranks the top 10 GitHub repositories most related to Forky’s conversation DAG and branching model. Persists GitHub Search API results insimilar_repos.jsonto make the analysis reproducible.Documentation
README.mdwith a focused similarity analysis: task scope, ranking criteria, and a ranked top‑10 list with rationales and links.Data
similar_repos.jsoncontaining the original GitHub Search API results (name, URL, description, topics, stars) used to generate the ranking.Written for commit aa8dad7. Summary will update on new commits.