mirror of
https://github.com/anthropics/claude-code-action.git
synced 2026-01-23 15:04:13 +08:00
* feat: implement Claude Code GitHub Action v1.0 with auto-detection and slash commands
Major features:
- Mode auto-detection based on GitHub event type
- Unified prompt field replacing override_prompt and direct_prompt
- Slash command system with pre-built commands
- Full backward compatibility with v0.x
Key changes:
- Add mode detector for automatic mode selection
- Implement slash command loader with YAML frontmatter support
- Update action.yml with new prompt input
- Create pre-built slash commands for common tasks
- Update all tests for v1.0 compatibility
Breaking changes (with compatibility):
- Mode input now optional (auto-detected)
- override_prompt deprecated (use prompt)
- direct_prompt deprecated (use prompt)
* test + formatting fixes
* feat: simplify to two modes (tag and agent) for v1.0
BREAKING CHANGES:
- Remove review mode entirely - now handled via slash commands in agent mode
- Remove all deprecated backward compatibility fields (mode, anthropic_model, override_prompt, direct_prompt)
- Simplify mode detection: prompt overrides everything, then @claude mentions trigger tag mode, default is agent mode
- Remove slash command resolution from GitHub Action - Claude Code handles natively
- Remove variable substitution - prompts passed through as-is
Architecture changes:
- Only two modes now: tag (for @claude mentions) and agent (everything else)
- Agent mode is the default for all events including PRs
- Users configure behavior via prompts/slash commands (e.g. /review)
- GitHub Action is now a thin wrapper that passes prompts to Claude Code
- Mode names changed: 'experimental-review' → removed entirely
This aligns with the philosophy that the GitHub Action should do minimal work and delegate to Claude Code for all intelligent behavior.
* fix: address PR review comments for v1.0 simplification
- Remove duplicate prompt field spread (line 160)
- Remove async from generatePrompt since slash commands are handled by Claude Code
- Add detailed comment explaining why prompt → agent mode logic
- Remove entire slash-commands loader and directories as Claude Code handles natively
- Simplify prompt generation to just pass through to Claude Code
These changes align with v1.0 philosophy: GitHub Action is a thin wrapper
that delegates everything to Claude Code for native handling.
* chore: remove unused js-yaml dependencies
These were added for slash-command YAML parsing but are no longer
needed since we removed slash-command preprocessing entirely
* fix: remove experimental-review mode reference from MCP config
The inline comment server configuration was checking for deprecated
'mode' field. Since review mode is removed in v1.0, this conditional
block is no longer needed.
* prettify
* feat: add claudeArgs input for direct CLI argument passing
- Add claude_args input to both action.yml files
- Implement shell-style argument parsing with quote handling
- Pass arguments directly to Claude CLI for maximum flexibility
- Add comprehensive tests for argument parsing
- Log custom arguments for debugging
Users can now pass any Claude CLI arguments directly:
claude_args: '--max-turns 3 --mcp-config /path/to/config.json'
This provides power users full control over Claude's behavior without
waiting for specific inputs to be added to the action.
* refactor: use industry-standard shell-quote for argument parsing
- Replace custom parseShellArgs with battle-tested shell-quote package
- Simplify code by removing unnecessary -p filtering (Claude handles it)
- Update tests to use shell-quote directly
- Add example workflow showing claude_args usage
This provides more robust argument parsing while reducing code complexity.
* bun format
* feat: add claudeArgs input for direct CLI argument passing
- Add claude_args input to action.yml for flexible CLI control
- Parse arguments with industry-standard shell-quote library
- Maintain proper argument order: -p [claudeArgs] [legacy] [BASE_ARGS]
- Keep tag mode defaults (needed for functionality)
- Agent mode has no defaults (full user control)
- Add comprehensive tests for new functionality
- Add example workflow showing usage
* format
* refactor: complete v1.0 simplification by removing all legacy inputs
- Remove all backward compatibility for v1.0 simplification
- Remove 10 legacy inputs from base-action/action.yml
- Remove 9 legacy inputs from main action.yml
- Simplify ClaudeOptions type to just timeoutMinutes and claudeArgs
- Remove all legacy option handling from prepareRunConfig
- Update tests to remove references to deleted fields
- Remove obsolete test file github/context.test.ts
- Clean up types to remove customInstructions, allowedTools, disallowedTools
Users now use claudeArgs exclusively for CLI control.
* fix: update MCP server tests after removing additionalPermissions
- Change github_ci server logic to check for workflow token presence
- Update test names to reflect new behavior
- Fix test that was incorrectly setting workflow token
* model version update
* Update package json
* remove deprecated workflow file (tests features we no longer support)
* Simplify agent mode and re-add additional_permissions input
- Agent mode now only triggers when explicit prompt is provided
- Removed automatic triggering for workflow_dispatch/schedule without prompt
- Re-added additional_permissions input for requesting GitHub permissions
- Fixed TypeScript types for mock context helpers to properly handle partial inputs
- Updated documentation to reflect simplified mode behavior
* Fix MCP config not being passed to Claude CLI
The MCP servers (including github_comment server) were configured but not passed to Claude. This caused the "update_claude_comment" tool to be unavailable.
Changes:
- Write MCP config to a file at $RUNNER_TEMP/claude-mcp-config.json
- Add mcp_config_file output from prepare.ts
- Pass MCP config file via --mcp-config flag in claude_args
- Use fs/promises writeFile to match codebase conventions
* Fix MCP tool availability and shell escaping in tag mode
Pass MCP config and allowed tools through claude_args to ensure tools like
mcp__github_comment__update_claude_comment are properly available to Claude CLI.
Key changes:
- Tag mode outputs claude_args with MCP config (as JSON string) and allowed tools
- Fixed shell escaping vulnerability when JSON contains single quotes
- Agent mode passes through user-provided claude_args unchanged
- Re-added mcp_config input for users to provide custom MCP servers
- Cleaned up misleading comments and unused file operations
- Clarified test workflow is for fork testing
Security fix: Properly escape single quotes in MCP config JSON to prevent
shell injection vulnerabilities.
Co-Authored-By: Claude <noreply@anthropic.com>
* bun format
* tests, typecheck, format
* registry test update
* Update agent mode to have github server as a default
* Fix agent mode to include GitHub MCP server with proper token
* Simplify review workflow - prevent multiple submissions
- Rename workflow to avoid conflicts
- Remove review submission tools
- Keep only essential tools for reading and analyzing PR
* Add GitHub MCP server and context prefix to agent mode
- Include main GitHub MCP server (Docker-based) by default
- Fetch and prefix GitHub context to prompts when in PR/issue context
- Users no longer need to manually configure GitHub tools
* Delete .github/workflows/claude-auto-review-test.yml
* Remove github_comment and inline_comment servers from agent mode defaults
- Agent mode now only includes the main GitHub MCP server by default
- Users can add additional servers via mcp_config if needed
- Reduces unnecessary MCP server overhead
* Remove all default MCP servers from agent mode
Agent mode now starts with no default servers - users must explicitly configure any MCP servers they need via mcp_config input
* Remove GitHub context prefixing and clean up agent mode
- Remove automatic GitHub context fetching and prefixing
- Remove unused imports (fetcher, formatter, context checks)
- Clean up comments
- Agent mode now simply passes through the user's prompt as-is
* Add GitHub MCP support to agent mode
- Parse --allowedTools from claude_args to detect when user wants GitHub MCPs
- Wire up github_inline_comment server in prepareMcpConfig for PR contexts
- Update agent mode to use prepareMcpConfig instead of manual config
- Add comprehensive tests for parseAllowedTools edge cases
- Fix TypeScript types to support both entity and automation contexts
* Format code with prettier
* Fix agent mode test to expect branch values
* Fix agent test to handle dynamic branch names from environment
* Better fix: Control environment variables in agent test for predictable behavior
* minor formatting
* Simplify MCP configuration to use multiple --mcp-config flags
- Remove MCP config merging logic from prepareMcpConfig
- Update agent and tag modes to pass multiple --mcp-config flags
- Let Claude handle config merging natively through multiple flags
- Fix TypeScript errors in test file
This approach is cleaner and relies on Claude's built-in support for multiple --mcp-config flags instead of manual JSON merging.
* feat: Copy project subagents to Claude runtime environment
Enables custom subagents defined in .claude/agents/ to work in GitHub Actions by:
- Checking for project agents in GITHUB_WORKSPACE/.claude/agents/
- Creating ~/.claude/agents/ directory if needed
- Copying all .md agent files to Claude's runtime location
- Following same pattern as slash commands for consistency
Includes comprehensive test coverage for the new functionality.
* formatting
* Add auto-fix CI workflows with slash command and inline approaches
- Add /fix-ci slash command for programmatic CI failure fixing
- Create auto-fix-ci.yml workflow using slash command approach
- Create auto-fix-ci-inline.yml workflow with full inline prompt
- Both workflows automatically analyze CI failures and create fix branches
* Add workflow_run event support and auto-fix CI workflows
- Add support for workflow_run event type in GitHub context
- Create /fix-ci slash command for programmatic CI failure fixing
- Add auto-fix-ci.yml workflow using slash command approach
- Add auto-fix-ci-inline.yml workflow with full inline prompt
- Both workflows automatically analyze CI failures and create fix branches
- Fix workflow syntax issues with optional chaining operator
* Use proper WorkflowRunEvent type instead of any
* bun formatting
* Remove auto-fix workflows and commands from v1-dev
These files should only exist in km-anthropic fork:
- .github/workflows/auto-fix-ci.yml
- .github/workflows/auto-fix-ci-inline.yml
- slash-commands/fix-ci.md
- .claude/commands/fix-ci.md
The workflow_run event support remains as it's useful for general automation.
* feat: Expose GitHub token as action output for external use
This allows workflows to use the Claude App token obtained by the action
for posting comments as claude[bot] instead of github-actions[bot].
Changes:
- Add github_token output to action.yml
- Export token from prepare.ts after authentication
- Allows workflows to use the same token Claude uses internally
* Debug: Add logging and always output github_token in prepare step
* Fix: Add git authentication to agent mode
Agent mode now fetches the authenticated user (claude[bot] when using Claude App token)
and configures git identity properly, matching the behavior of tag mode.
This fixes the issue where commits in agent mode were failing due to missing git identity.
* minor bun format
* remove unnecessary file
* fix: Add branch environment variable support to agent mode for signed commits
- Read CLAUDE_BRANCH and BASE_BRANCH env vars in agent mode
- Pass correct branch info to MCP file ops server
- Enables signed auto-fix workflows to create branches via API
* feat: Add auto-fix CI workflow examples
- Add auto-fix-ci example with inline git commits
- Add auto-fix-ci-signed example with signed commits via MCP
- Include corresponding slash commands for both workflows
- Examples demonstrate automated CI failure detection and fixing
* fix: Fix TypeScript error in agent mode git config
- Remove dependency on configureGitAuth which expects ParsedGitHubContext
- Implement git configuration directly for automation contexts
- Properly handle git authentication for agent mode
* fix: Align agent mode git config with existing patterns
- Use GITHUB_SERVER_URL from config module consistently
- Remove existing headers before setting new ones
- Use remote URL with embedded token like git-config.ts does
- Match the existing git authentication pattern in the codebase
* refactor: Use shared configureGitAuth function in agent mode
- Update configureGitAuth to accept GitHubContext instead of ParsedGitHubContext
- This allows both tag mode and agent mode to use the same function
- Removes code duplication and ensures consistent git configuration
* feat: Improve error message for 403 permission errors when committing
When the github_file_ops MCP server gets a 403 error, it now shows a cleaner
message suggesting to rebase from main/master branch to fix the issue.
* docs: Update documentation for v1.0 release (#476)
* docs: Update documentation for v1.0 release
- Integrate breaking changes naturally without alarming users
- Replace deprecated inputs (direct_prompt, custom_instructions, mode) with new unified approach
- Update all examples to use prompt and claude_args instead of deprecated inputs
- Add migration guides to help users transition from v0.x to v1.0
- Emphasize automatic mode detection as a key feature
- Update all workflow examples to @v1 from @beta
- Document how claude_args provides direct CLI control
- Update FAQ with automatic mode detection explanation
- Convert all tool configuration to use claude_args format
* fix: Apply prettier formatting to documentation files
* fix: Update all Claude model versions to latest and improve documentation accuracy
- Update all model references to claude-4-0-sonnet-20250805 (latest Sonnet 4)
- Update Bedrock models to anthropic.claude-4-0-sonnet-20250805-v1:0
- Update Vertex models to claude-4-0-sonnet@20250805
- Fix cloud-providers.md to use claude_args instead of deprecated model input
- Ensure all examples use @v1 instead of @beta
- Keep claude-opus-4-1-20250805 in examples where Opus is demonstrated
- Align all documentation with v1.0 patterns consistently
* feat: Add dedicated migration guide as requested in PR feedback
- Create comprehensive migration-guide.md with step-by-step instructions
- Add prominent links to migration guide in README.md
- Update usage.md to reference the separate migration guide
- Include before/after examples for all common scenarios
- Add checklist for systematic migration
- Address Ashwin's feedback about having a separate, clearly linked migration guide
* feat: Add comprehensive examples for hero use cases
- Add dedicated issue deduplication workflow example
- Add issue triage example (moved from .github/workflows)
- Update all examples to use v1-dev branch consistently
- Enable MCP tools in claude-auto-review.yml
- Consolidate PR review examples into single comprehensive example
Hero use cases now covered:
1. Code reviews (claude-auto-review.yml)
2. Issue triaging (issue-triage.yml)
3. Issue deduplication (issue-deduplication.yml)
4. Auto-fix CI failures (auto-fix-ci/auto-fix-ci.yml)
All examples updated to follow v1-dev paradigm with proper prompt and claude_args configuration.
* refactor: Remove timeout_minutes parameter from action (#482)
This change removes the custom timeout_minutes parameter from the action in favor of using GitHub Actions' native timeout-minutes feature.
Changes:
- Removed timeout_minutes input from action.yml and base-action/action.yml
- Removed all timeout handling logic from base-action/src/run-claude.ts
- Updated base-action/src/index.ts to remove timeoutMinutes parameter
- Removed timeout-related tests from base-action/test/run-claude.test.ts
- Removed timeout_minutes from all example workflow files (19 files)
Rationale:
- Simplifies the codebase by removing custom timeout logic
- Users can use GitHub Actions' native timeout-minutes at the job/step level
- Reduces complexity and maintenance burden
- Follows GitHub Actions best practices
BREAKING CHANGE: The timeout_minutes parameter is no longer supported. Users should use GitHub Actions' native timeout-minutes instead.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* refactor: Remove unused slash commands and agents copying logic
Removes experimental file copying features that had no default content:
- Removed experimental_slash_commands_dir parameter and related logic
- Removed automatic project agents copying from .claude/agents/
- Eliminated flaky error-prone cp operations with stderr suppression
- Removed 175 lines of unused code and associated tests
These features were infrastructure without default content that used
problematic error handling patterns (2>/dev/null || true) which could
hide real filesystem errors.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: Remove references to timeout_minutes parameter
The timeout_minutes parameter was removed in commit 986e40a but
documentation still referenced it. This updates:
- docs/usage.md: Removed timeout_minutes from inputs table
- base-action/README.md: Removed from inputs table and example
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kashyap Murali <13315300+katchu11@users.noreply.github.com>
678 lines
21 KiB
JavaScript
678 lines
21 KiB
JavaScript
#!/usr/bin/env node
|
|
// GitHub File Operations MCP Server
|
|
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
|
|
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
|
|
import { z } from "zod";
|
|
import { readFile, stat } from "fs/promises";
|
|
import { join } from "path";
|
|
import { constants } from "fs";
|
|
import fetch from "node-fetch";
|
|
import { GITHUB_API_URL } from "../github/api/config";
|
|
import { retryWithBackoff } from "../utils/retry";
|
|
|
|
type GitHubRef = {
|
|
object: {
|
|
sha: string;
|
|
};
|
|
};
|
|
|
|
type GitHubCommit = {
|
|
tree: {
|
|
sha: string;
|
|
};
|
|
};
|
|
|
|
type GitHubTree = {
|
|
sha: string;
|
|
};
|
|
|
|
type GitHubNewCommit = {
|
|
sha: string;
|
|
message: string;
|
|
author: {
|
|
name: string;
|
|
date: string;
|
|
};
|
|
};
|
|
|
|
// Get repository information from environment variables
|
|
const REPO_OWNER = process.env.REPO_OWNER;
|
|
const REPO_NAME = process.env.REPO_NAME;
|
|
const BRANCH_NAME = process.env.BRANCH_NAME;
|
|
const REPO_DIR = process.env.REPO_DIR || process.cwd();
|
|
|
|
if (!REPO_OWNER || !REPO_NAME || !BRANCH_NAME) {
|
|
console.error(
|
|
"Error: REPO_OWNER, REPO_NAME, and BRANCH_NAME environment variables are required",
|
|
);
|
|
process.exit(1);
|
|
}
|
|
|
|
const server = new McpServer({
|
|
name: "GitHub File Operations Server",
|
|
version: "0.0.1",
|
|
});
|
|
|
|
// Helper function to get or create branch reference
|
|
async function getOrCreateBranchRef(
|
|
owner: string,
|
|
repo: string,
|
|
branch: string,
|
|
githubToken: string,
|
|
): Promise<string> {
|
|
// Try to get the branch reference
|
|
const refUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs/heads/${branch}`;
|
|
const refResponse = await fetch(refUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
if (refResponse.ok) {
|
|
const refData = (await refResponse.json()) as GitHubRef;
|
|
return refData.object.sha;
|
|
}
|
|
|
|
if (refResponse.status !== 404) {
|
|
throw new Error(`Failed to get branch reference: ${refResponse.status}`);
|
|
}
|
|
|
|
const baseBranch = process.env.BASE_BRANCH!;
|
|
|
|
// Get the SHA of the base branch
|
|
const baseRefUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs/heads/${baseBranch}`;
|
|
const baseRefResponse = await fetch(baseRefUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
let baseSha: string;
|
|
|
|
if (!baseRefResponse.ok) {
|
|
// If base branch doesn't exist, try default branch
|
|
const repoUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}`;
|
|
const repoResponse = await fetch(repoUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
if (!repoResponse.ok) {
|
|
throw new Error(`Failed to get repository info: ${repoResponse.status}`);
|
|
}
|
|
|
|
const repoData = (await repoResponse.json()) as {
|
|
default_branch: string;
|
|
};
|
|
const defaultBranch = repoData.default_branch;
|
|
|
|
// Try default branch
|
|
const defaultRefUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs/heads/${defaultBranch}`;
|
|
const defaultRefResponse = await fetch(defaultRefUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
if (!defaultRefResponse.ok) {
|
|
throw new Error(
|
|
`Failed to get default branch reference: ${defaultRefResponse.status}`,
|
|
);
|
|
}
|
|
|
|
const defaultRefData = (await defaultRefResponse.json()) as GitHubRef;
|
|
baseSha = defaultRefData.object.sha;
|
|
} else {
|
|
const baseRefData = (await baseRefResponse.json()) as GitHubRef;
|
|
baseSha = baseRefData.object.sha;
|
|
}
|
|
|
|
// Create the new branch using the same pattern as octokit
|
|
const createRefUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs`;
|
|
const createRefResponse = await fetch(createRefUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
ref: `refs/heads/${branch}`,
|
|
sha: baseSha,
|
|
}),
|
|
});
|
|
|
|
if (!createRefResponse.ok) {
|
|
const errorText = await createRefResponse.text();
|
|
throw new Error(
|
|
`Failed to create branch: ${createRefResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
console.log(`Successfully created branch ${branch}`);
|
|
return baseSha;
|
|
}
|
|
|
|
// Get the appropriate Git file mode for a file
|
|
async function getFileMode(filePath: string): Promise<string> {
|
|
try {
|
|
const fileStat = await stat(filePath);
|
|
if (fileStat.isFile()) {
|
|
// Check if execute bit is set for user
|
|
if (fileStat.mode & constants.S_IXUSR) {
|
|
return "100755"; // Executable file
|
|
} else {
|
|
return "100644"; // Regular file
|
|
}
|
|
} else if (fileStat.isDirectory()) {
|
|
return "040000"; // Directory (tree)
|
|
} else if (fileStat.isSymbolicLink()) {
|
|
return "120000"; // Symbolic link
|
|
} else {
|
|
// Fallback for unknown file types
|
|
return "100644";
|
|
}
|
|
} catch (error) {
|
|
// If we can't stat the file, default to regular file
|
|
console.warn(
|
|
`Could not determine file mode for ${filePath}, using default: ${error}`,
|
|
);
|
|
return "100644";
|
|
}
|
|
}
|
|
|
|
// Commit files tool
|
|
server.tool(
|
|
"commit_files",
|
|
"Commit one or more files to a repository in a single commit (this will commit them atomically in the remote repository)",
|
|
{
|
|
files: z
|
|
.array(z.string())
|
|
.describe(
|
|
'Array of file paths relative to repository root (e.g. ["src/main.js", "README.md"]). All files must exist locally.',
|
|
),
|
|
message: z.string().describe("Commit message"),
|
|
},
|
|
async ({ files, message }) => {
|
|
const owner = REPO_OWNER;
|
|
const repo = REPO_NAME;
|
|
const branch = BRANCH_NAME;
|
|
try {
|
|
const githubToken = process.env.GITHUB_TOKEN;
|
|
if (!githubToken) {
|
|
throw new Error("GITHUB_TOKEN environment variable is required");
|
|
}
|
|
|
|
const processedFiles = files.map((filePath) => {
|
|
if (filePath.startsWith("/")) {
|
|
return filePath.slice(1);
|
|
}
|
|
return filePath;
|
|
});
|
|
|
|
// 1. Get the branch reference (create if doesn't exist)
|
|
const baseSha = await getOrCreateBranchRef(
|
|
owner,
|
|
repo,
|
|
branch,
|
|
githubToken,
|
|
);
|
|
|
|
// 2. Get the base commit
|
|
const commitUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/commits/${baseSha}`;
|
|
const commitResponse = await fetch(commitUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
if (!commitResponse.ok) {
|
|
throw new Error(`Failed to get base commit: ${commitResponse.status}`);
|
|
}
|
|
|
|
const commitData = (await commitResponse.json()) as GitHubCommit;
|
|
const baseTreeSha = commitData.tree.sha;
|
|
|
|
// 3. Create tree entries for all files
|
|
const treeEntries = await Promise.all(
|
|
processedFiles.map(async (filePath) => {
|
|
const fullPath = filePath.startsWith("/")
|
|
? filePath
|
|
: join(REPO_DIR, filePath);
|
|
|
|
// Get the proper file mode based on file permissions
|
|
const fileMode = await getFileMode(fullPath);
|
|
|
|
// Check if file is binary (images, etc.)
|
|
const isBinaryFile =
|
|
/\.(png|jpg|jpeg|gif|webp|ico|pdf|zip|tar|gz|exe|bin|woff|woff2|ttf|eot)$/i.test(
|
|
filePath,
|
|
);
|
|
|
|
if (isBinaryFile) {
|
|
// For binary files, create a blob first using the Blobs API
|
|
const binaryContent = await readFile(fullPath);
|
|
|
|
// Create blob using Blobs API (supports encoding parameter)
|
|
const blobUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/blobs`;
|
|
const blobResponse = await fetch(blobUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
content: binaryContent.toString("base64"),
|
|
encoding: "base64",
|
|
}),
|
|
});
|
|
|
|
if (!blobResponse.ok) {
|
|
const errorText = await blobResponse.text();
|
|
throw new Error(
|
|
`Failed to create blob for ${filePath}: ${blobResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
const blobData = (await blobResponse.json()) as { sha: string };
|
|
|
|
// Return tree entry with blob SHA
|
|
return {
|
|
path: filePath,
|
|
mode: fileMode,
|
|
type: "blob",
|
|
sha: blobData.sha,
|
|
};
|
|
} else {
|
|
// For text files, include content directly in tree
|
|
const content = await readFile(fullPath, "utf-8");
|
|
return {
|
|
path: filePath,
|
|
mode: fileMode,
|
|
type: "blob",
|
|
content: content,
|
|
};
|
|
}
|
|
}),
|
|
);
|
|
|
|
// 4. Create a new tree
|
|
const treeUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/trees`;
|
|
const treeResponse = await fetch(treeUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
base_tree: baseTreeSha,
|
|
tree: treeEntries,
|
|
}),
|
|
});
|
|
|
|
if (!treeResponse.ok) {
|
|
const errorText = await treeResponse.text();
|
|
throw new Error(
|
|
`Failed to create tree: ${treeResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
const treeData = (await treeResponse.json()) as GitHubTree;
|
|
|
|
// 5. Create a new commit
|
|
const newCommitUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/commits`;
|
|
const newCommitResponse = await fetch(newCommitUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
message: message,
|
|
tree: treeData.sha,
|
|
parents: [baseSha],
|
|
}),
|
|
});
|
|
|
|
if (!newCommitResponse.ok) {
|
|
const errorText = await newCommitResponse.text();
|
|
throw new Error(
|
|
`Failed to create commit: ${newCommitResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
const newCommitData = (await newCommitResponse.json()) as GitHubNewCommit;
|
|
|
|
// 6. Update the reference to point to the new commit
|
|
const updateRefUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs/heads/${branch}`;
|
|
|
|
// We're seeing intermittent 403 "Resource not accessible by integration" errors
|
|
// on certain repos when updating git references. These appear to be transient
|
|
// GitHub API issues that succeed on retry.
|
|
await retryWithBackoff(
|
|
async () => {
|
|
const updateRefResponse = await fetch(updateRefUrl, {
|
|
method: "PATCH",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
sha: newCommitData.sha,
|
|
force: false,
|
|
}),
|
|
});
|
|
|
|
if (!updateRefResponse.ok) {
|
|
const errorText = await updateRefResponse.text();
|
|
|
|
// Provide a more helpful error message for 403 permission errors
|
|
if (updateRefResponse.status === 403) {
|
|
const permissionError = new Error(
|
|
`Permission denied: Unable to push commits to branch '${branch}'. ` +
|
|
`Please rebase your branch from the main/master branch to allow Claude to commit.\n\n` +
|
|
`Original error: ${errorText}`,
|
|
);
|
|
throw permissionError;
|
|
}
|
|
|
|
// For other errors, use the original message
|
|
const error = new Error(
|
|
`Failed to update reference: ${updateRefResponse.status} - ${errorText}`,
|
|
);
|
|
|
|
// For non-403 errors, fail immediately without retry
|
|
console.error("Non-retryable error:", updateRefResponse.status);
|
|
throw error;
|
|
}
|
|
},
|
|
{
|
|
maxAttempts: 3,
|
|
initialDelayMs: 1000, // Start with 1 second delay
|
|
maxDelayMs: 5000, // Max 5 seconds delay
|
|
backoffFactor: 2, // Double the delay each time
|
|
},
|
|
);
|
|
|
|
const simplifiedResult = {
|
|
commit: {
|
|
sha: newCommitData.sha,
|
|
message: newCommitData.message,
|
|
author: newCommitData.author.name,
|
|
date: newCommitData.author.date,
|
|
},
|
|
files: processedFiles.map((path) => ({ path })),
|
|
tree: {
|
|
sha: treeData.sha,
|
|
},
|
|
};
|
|
|
|
return {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: JSON.stringify(simplifiedResult, null, 2),
|
|
},
|
|
],
|
|
};
|
|
} catch (error) {
|
|
const errorMessage =
|
|
error instanceof Error ? error.message : String(error);
|
|
return {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Error: ${errorMessage}`,
|
|
},
|
|
],
|
|
error: errorMessage,
|
|
isError: true,
|
|
};
|
|
}
|
|
},
|
|
);
|
|
|
|
// Delete files tool
|
|
server.tool(
|
|
"delete_files",
|
|
"Delete one or more files from a repository in a single commit",
|
|
{
|
|
paths: z
|
|
.array(z.string())
|
|
.describe(
|
|
'Array of file paths to delete relative to repository root (e.g. ["src/old-file.js", "docs/deprecated.md"])',
|
|
),
|
|
message: z.string().describe("Commit message"),
|
|
},
|
|
async ({ paths, message }) => {
|
|
const owner = REPO_OWNER;
|
|
const repo = REPO_NAME;
|
|
const branch = BRANCH_NAME;
|
|
try {
|
|
const githubToken = process.env.GITHUB_TOKEN;
|
|
if (!githubToken) {
|
|
throw new Error("GITHUB_TOKEN environment variable is required");
|
|
}
|
|
|
|
// Convert absolute paths to relative if they match CWD
|
|
const cwd = process.cwd();
|
|
const processedPaths = paths.map((filePath) => {
|
|
if (filePath.startsWith("/")) {
|
|
if (filePath.startsWith(cwd)) {
|
|
// Strip CWD from absolute path
|
|
return filePath.slice(cwd.length + 1);
|
|
} else {
|
|
throw new Error(
|
|
`Path '${filePath}' must be relative to repository root or within current working directory`,
|
|
);
|
|
}
|
|
}
|
|
return filePath;
|
|
});
|
|
|
|
// 1. Get the branch reference (create if doesn't exist)
|
|
const baseSha = await getOrCreateBranchRef(
|
|
owner,
|
|
repo,
|
|
branch,
|
|
githubToken,
|
|
);
|
|
|
|
// 2. Get the base commit
|
|
const commitUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/commits/${baseSha}`;
|
|
const commitResponse = await fetch(commitUrl, {
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
},
|
|
});
|
|
|
|
if (!commitResponse.ok) {
|
|
throw new Error(`Failed to get base commit: ${commitResponse.status}`);
|
|
}
|
|
|
|
const commitData = (await commitResponse.json()) as GitHubCommit;
|
|
const baseTreeSha = commitData.tree.sha;
|
|
|
|
// 3. Create tree entries for file deletions (setting SHA to null)
|
|
const treeEntries = processedPaths.map((path) => ({
|
|
path: path,
|
|
mode: "100644",
|
|
type: "blob" as const,
|
|
sha: null,
|
|
}));
|
|
|
|
// 4. Create a new tree with deletions
|
|
const treeUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/trees`;
|
|
const treeResponse = await fetch(treeUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
base_tree: baseTreeSha,
|
|
tree: treeEntries,
|
|
}),
|
|
});
|
|
|
|
if (!treeResponse.ok) {
|
|
const errorText = await treeResponse.text();
|
|
throw new Error(
|
|
`Failed to create tree: ${treeResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
const treeData = (await treeResponse.json()) as GitHubTree;
|
|
|
|
// 5. Create a new commit
|
|
const newCommitUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/commits`;
|
|
const newCommitResponse = await fetch(newCommitUrl, {
|
|
method: "POST",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
message: message,
|
|
tree: treeData.sha,
|
|
parents: [baseSha],
|
|
}),
|
|
});
|
|
|
|
if (!newCommitResponse.ok) {
|
|
const errorText = await newCommitResponse.text();
|
|
throw new Error(
|
|
`Failed to create commit: ${newCommitResponse.status} - ${errorText}`,
|
|
);
|
|
}
|
|
|
|
const newCommitData = (await newCommitResponse.json()) as GitHubNewCommit;
|
|
|
|
// 6. Update the reference to point to the new commit
|
|
const updateRefUrl = `${GITHUB_API_URL}/repos/${owner}/${repo}/git/refs/heads/${branch}`;
|
|
|
|
// We're seeing intermittent 403 "Resource not accessible by integration" errors
|
|
// on certain repos when updating git references. These appear to be transient
|
|
// GitHub API issues that succeed on retry.
|
|
await retryWithBackoff(
|
|
async () => {
|
|
const updateRefResponse = await fetch(updateRefUrl, {
|
|
method: "PATCH",
|
|
headers: {
|
|
Accept: "application/vnd.github+json",
|
|
Authorization: `Bearer ${githubToken}`,
|
|
"X-GitHub-Api-Version": "2022-11-28",
|
|
"Content-Type": "application/json",
|
|
},
|
|
body: JSON.stringify({
|
|
sha: newCommitData.sha,
|
|
force: false,
|
|
}),
|
|
});
|
|
|
|
if (!updateRefResponse.ok) {
|
|
const errorText = await updateRefResponse.text();
|
|
|
|
// Provide a more helpful error message for 403 permission errors
|
|
if (updateRefResponse.status === 403) {
|
|
console.log("Received 403 error, will retry...");
|
|
const permissionError = new Error(
|
|
`Permission denied: Unable to push commits to branch '${branch}'. ` +
|
|
`Please rebase your branch from the main/master branch to allow Claude to commit.\n\n` +
|
|
`Original error: ${errorText}`,
|
|
);
|
|
throw permissionError;
|
|
}
|
|
|
|
// For other errors, use the original message
|
|
const error = new Error(
|
|
`Failed to update reference: ${updateRefResponse.status} - ${errorText}`,
|
|
);
|
|
|
|
// For non-403 errors, fail immediately without retry
|
|
console.error("Non-retryable error:", updateRefResponse.status);
|
|
throw error;
|
|
}
|
|
},
|
|
{
|
|
maxAttempts: 3,
|
|
initialDelayMs: 1000, // Start with 1 second delay
|
|
maxDelayMs: 5000, // Max 5 seconds delay
|
|
backoffFactor: 2, // Double the delay each time
|
|
},
|
|
);
|
|
|
|
const simplifiedResult = {
|
|
commit: {
|
|
sha: newCommitData.sha,
|
|
message: newCommitData.message,
|
|
author: newCommitData.author.name,
|
|
date: newCommitData.author.date,
|
|
},
|
|
deletedFiles: processedPaths.map((path) => ({ path })),
|
|
tree: {
|
|
sha: treeData.sha,
|
|
},
|
|
};
|
|
|
|
return {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: JSON.stringify(simplifiedResult, null, 2),
|
|
},
|
|
],
|
|
};
|
|
} catch (error) {
|
|
const errorMessage =
|
|
error instanceof Error ? error.message : String(error);
|
|
return {
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: `Error: ${errorMessage}`,
|
|
},
|
|
],
|
|
error: errorMessage,
|
|
isError: true,
|
|
};
|
|
}
|
|
},
|
|
);
|
|
|
|
async function runServer() {
|
|
const transport = new StdioServerTransport();
|
|
await server.connect(transport);
|
|
process.on("exit", () => {
|
|
server.close();
|
|
});
|
|
}
|
|
|
|
runServer().catch(console.error);
|