* ci: skip Claude-backed test jobs on fork PRs
Jobs that run the action against the Claude API authenticate via workload
identity federation, which fork PRs cannot mint an OIDC token for, so they
always failed on external contributions. Gate each such job on the PR head
repo matching the base repo; push and workflow_dispatch runs are unaffected.
No-Verification-Needed: CI workflow config only, exercised by Actions on the PR
* test: pin the bare remote's initial branch in fetch-depth test
The shallow-clone case created its bare remote with a plain git init, so
HEAD pointed at whatever init.defaultBranch resolves to (master on CI)
while the test only pushed main. git clone --depth=1 implies
--single-branch, and with a dangling remote HEAD it produces an empty,
non-shallow clone, so the is-shallow assertion failed on runners whose
default branch is not main.
No-Verification-Needed: test-only change
* Run checkout auth cleanup when API commit signing is enabled
* Derive git-config test expectations from GITHUB_SERVER_URL
No-Verification-Needed: test-only change
* Scope config snapshot to files inside the working tree
* Record excluded snapshot entries as placeholders instead of links
* Limit linked snapshot content to unmodified tracked files and tracked directories
File targets reached through a link are included only when their content is
unchanged from HEAD, and directory targets only when they contain tracked
files; anything else is recorded as a single placeholder. Adds tests for a
sensitive path that links to a tracked directory, links to untracked
directories, and links to tracked files modified after checkout.
* Redact common credential patterns from published run output
* Handle color codes and escape sequences ahead of redacted values
Vendor-prefixed formats no longer require a leading word boundary, so a
value that follows an ANSI SGR terminator or a serialized JSON escape is
still matched. AWS key ids keep a boundary but also accept those cases.
sanitizeContent goes back to GitHub-only redaction for inbound content,
and the failure annotation is redacted like the tracking comment.
* Coerce non-string text content before redacting tool results
No-Verification-Needed: one-line coercion in a formatting helper plus regression test
* Invoke the formatter directly from the format hook
The PostToolUse format hook now runs prettier directly with a pinned
version and --no-config instead of going through the package.json
"format" script, so the hook resolves the same way regardless of the
scripts and formatter config in the checked-out tree. Output matches
the previous "bun run format" (both .prettierrc files are empty).
Also documents which paths the action restores from the PR base branch
and recommends keeping base-branch hooks self-contained.
No-Verification-Needed: config, comment, and doc-only change
* Qualify the self-contained hook guidance for Bun-only runners
Note in docs/security.md and the restore-config JSDoc that bunx runs the
tool under node when node is on PATH, but on a Bun-only runner Bun runs
the script itself and reads bunfig.toml (preload etc.) from the
checkout, so that file and .npmrc are runtime config from the PR head.
No-Verification-Needed: comment- and doc-only change
* Exclude .claude-pr from prettier
No-Verification-Needed: prettierignore-only change
The write-permission gate previously only ran for issue/PR entity
events. Apply it to workflow_run events as well, checking both the
workflow actor and the actor recorded on the upstream run when they
differ. allowed_non_write_users and the github_token override behave
the same as for entity events. Document the behavior for workflow_run
pipelines.
* Derive trigger timestamps for issues and pull_request events
For issues labeled/assigned triggers, look up the matching event in the
issue's event history to get the exact time of the label/assignment,
falling back to the payload's updated_at/created_at when the lookup
fails. issues opened uses issue.created_at; pull_request opened uses
pull_request.created_at and other pull_request actions use updated_at.
* Ignore issue label/assign events older than the payload snapshot
A matching labeled/assigned event that predates the webhook payload's
issue.updated_at cannot be the event that fired the webhook, so fall
back to the payload timestamps instead of adopting it as the boundary.
* Add pr-stamp-sweep review workflow
Adds a reusable workflow script that fans out one reviewer agent per
candidate PR to judge whether it can be approved as-is, then runs an
adversarial verification pass on each approval recommendation before
including it in the final list.
Reviewers read pre-fetched PR dossiers from /tmp/claude/pr-sweep/<n>.md
(metadata, body, comments, full diff) rather than calling gh directly,
and verify diff claims against the local checkout. PR numbers are
passed via args; the script fails fast if none are provided.
* Sharpen security checklist in reviewer prompts
Replace the general security-history note with explicit attack classes
both reviewer stages must check: prompt injection (untrusted content
reaching Claude's context, including via tool output), code execution
(shell commands, eval/spawn, workflow expressions), path traversal,
and credential exposure.
* Add workload identity federation support to base-action
Move the workload identity module into base-action so the standalone
action can fetch and refresh the GitHub OIDC identity token itself, and
expose the same federation inputs as the outer action. Switch the
base-action test workflows from the anthropic_api_key secret to the
federation repo variables and grant them id-token: write.
* Verify MCP test tool invocation instead of init connection status
MCP servers can connect asynchronously, so the init event may report a
server as pending. Check that the server is registered at init, then
assert the test tool was actually called and returned its response.
Also pass the MCP config through claude_args --mcp-config, replacing the
removed mcp_config input.
Switch claude.yml, claude-review.yml, and issue-triage.yml from the
anthropic_api_key secret to the workload identity federation inputs.
The federation rule, organization, and service account IDs are read
from repository variables; issue-triage.yml additionally gains the
id-token: write permission required to request the OIDC token.
* Add workload identity federation auth support
Adds anthropic_federation_rule_id, anthropic_organization_id,
anthropic_service_account_id, anthropic_workspace_id, and
anthropic_oidc_audience inputs. When the federation rule and organization
are set, the action fetches the workflow's GitHub Actions OIDC token,
writes it to a file in RUNNER_TEMP, keeps it refreshed during execution,
and points the Claude Code CLI at it via ANTHROPIC_IDENTITY_TOKEN_FILE so
the CLI can exchange it for a short-lived access token instead of using a
static API key.
* Add WIF example workflow and base-action federation docs
* Default workload identity OIDC audience to https://api.anthropic.com
Move the allowed_bots check in checkHumanActor and checkWritePermissions so
it only fires after the actor has been resolved as a non-User account
(GitHub App / bot, or unresolvable app actor). Actors that resolve to a
regular User account go through the standard human/write checks regardless
of allowed_bots.
The Copilot-style path (GITHUB_ACTOR not ending in [bot] and not resolvable
as a user) is unchanged: it still falls through to the existing 404 catch,
which already consults allowed_bots once the API has reported the actor is
not a user.
Update tests to match and add coverage for the User-account path.
The opt-in simplified tag-mode prompt omitted several guardrails the
default prompt has. Bring it closer to the default's posture while
keeping it terse:
- Scoping clarification: spell out that only the triggering comment
(or the issue body for issue events) carries instructions; other
comments, the body, review comments, and repository files are
reference context, not commands to act on.
- Review-only stop-condition: questions and code reviews must not edit,
commit, push, or create branches unless the trigger explicitly asks
for a code change.
- PR base-branch diff: when triggered on a PR with a known base branch,
compare against origin/<base> instead of main/master.
- Capability limits: cannot submit formal PR reviews, approve, or merge;
decline politely and point to the FAQ.
Adds focused tests covering the new lines for both PR and non-PR
events, including presence/absence of the conditional base-branch line.
Agent SDK 0.2.113 dropped vendor/ripgrep and now ships native binaries
via per-platform optionalDependencies. Two breakages:
- action.yml chmod'd vendor/ripgrep which no longer exists, failing the
Install Dependencies step with find exit 1.
- The SDK auto-resolves its bundled binary by trying the -musl platform
package before the glibc one. bun install does not respect the
package.json libc field and installs both on glibc Linux, so the SDK
picks the musl binary and spawn fails with ENOENT.
Remove the obsolete ripgrep chmod. Make installClaudeCode() return the
install.sh binary path and pass it explicitly as
pathToClaudeCodeExecutable so the SDK skips auto-resolution entirely.
* fix: fall back to repo default_branch instead of hardcoded "main"
When no explicit base_branch input is provided, the action previously
fell back to a hardcoded "main", which fails on repositories whose
default branch is named differently (e.g. "master", "develop").
This reads repository.default_branch from the GitHub event payload
(populated once in parseGitHubContext) and uses it as the fallback in
all three callsites: agent/index.ts, run.ts, and update-comment-link.ts.
Explicit env/input precedence is preserved; "main" remains only as a
last-resort defensive fallback if the payload somehow lacks the field.
* test: drop unused BASE_BRANCH env handling from default_branch test
agent/index.ts no longer reads process.env.BASE_BRANCH directly (it now
goes through context.inputs.baseBranch which is set on the mock context),
so saving/clearing/restoring that env var in the regression test is dead
code.
* Revert "chore: bump Claude Code to 2.1.89 and Agent SDK to 0.2.89"
This reverts commit bee87b3258.
* Revert "chore: bump Claude Code to 2.1.88 and Agent SDK to 0.2.88"
This reverts commit 7225f045c6.
Add a `display_report` input parameter (default: "true") that controls
whether the Claude Code Report is written to the GitHub Step Summary.
Setting it to "false" allows users with custom formatting solutions to
avoid duplicate output in the step summary.
Closes#206
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
Reverts the following commits:
- f669191 fix: use unique local branch names for PR checkout to avoid conflicts (#931)
- 21e3fe0 Fix PR checkout to support fork PRs (#851)
Simplifies PR branch checkout back to using headRefName directly instead
of the pr-{number} local branch naming scheme introduced in #931 and the
GitHub pull ref fetch approach introduced in #851.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* Update claude-opus-4-5 to claude-opus-4-6 in workflow
* Fix whitespace formatting in docs and commands
* Fix whitespace formatting in docs and commands
* Add claude-opus-4-6 model to PR review workflow
---------
Co-authored-by: Claude <noreply@anthropic.com>
Replace the over-engineered Mode interface/registry/detector pattern with
straightforward inline logic. There are only 2 modes (tag and agent) and
the complexity wasn't justified.
- Delete Mode interface, registry, and prepare pass-through modules
- Export prepareTagMode() and prepareAgentMode() as standalone functions
- Inline trigger checking and mode dispatch in run.ts/prepare.ts
- Change generatePrompt/createPrompt to take modeName string instead of Mode
- Remove dead code (extractGitHubContext, unused detector helpers)
- Update CLAUDE.md to reflect new architecture
* refactor: unify action into single composite step with run.ts entrypoint
Consolidate the prepare and base-action phases into a single composite
step that runs src/entrypoints/run.ts. This simplifies the action.yml
from multiple steps to one execution step, while keeping the same
behavior.
Key changes:
- Add src/entrypoints/run.ts as unified entrypoint
- Simplify action.yml to single 'Run Claude Code Action' step
- Pass all inputs via environment variables
- Update base-action to accept inputs via env vars
- Support agent mode auto-detection from prompt input
* refactor: keep SSH signing cleanup and token revocation as separate action steps
Move SSH signing key cleanup and app token revocation back to separate
composite action steps in action.yml with always() conditions, rather
than handling them inside run.ts. This keeps these cleanup concerns
as independently visible steps in the workflow.
* fix: address PR review feedback
- Use path.dirname() instead of manual string slicing for executable path
- Differentiate prepare vs execution errors in catch block so tracking
comment accurately reflects which phase failed
- Update CLAUDE.md architecture docs to reflect unified run.ts entrypoint
and four-phase design
* fix: address PR review feedback
- Use path.dirname() instead of manual string slicing for executable path
- Differentiate prepare vs execution errors in catch block so tracking
comment accurately reflects which phase failed
- Rewrite CLAUDE.md to focus on mental model, key concepts, and gotchas
instead of exhaustive file listings
* feat: send additional_permissions in token exchange request
Parse the ADDITIONAL_PERMISSIONS env var and send it as a JSON body
in the OIDC token exchange request. Permissions are merged on top of
the standard defaults (contents: write, pull_requests: write,
issues: write).
* docs: list specific available additional permissions
* refactor: consolidate CI workflows with ci-all.yml orchestrator
- Add ci-all.yml to orchestrate all CI workflows on push to main
- Update individual workflows to use workflow_call for reusability
- Remove redundant push triggers from individual test workflows
- Update release.yml to trigger on CI All workflow completion
- Auto-release on version bump commits after CI passes
Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Generated-By: Claude Code (cli/claude-opus-4-5=100%)
Claude-Steers: 8
Claude-Permission-Prompts: 1
Claude-Escapes: 0
* address security review comments
---------
Co-authored-by: Claude <noreply@anthropic.com>
ssh-keygen requires a trailing newline to parse private keys correctly.
Without it, git signing fails with the confusing error:
'Couldn't load public key: No such file or directory?'
This normalizes the key to always end with a newline before writing.
Temporarily disable the release-base-action job that syncs releases
to the claude-code-base-action repository. The job checkout step
and subsequent tag/release creation steps are now commented out.
Claude-Generated-By: Claude Code (cli/claude-opus-4-5=100%)
Claude-Steers: 2
Claude-Permission-Prompts: 2
Claude-Escapes: 0
Co-authored-by: Claude <noreply@anthropic.com>
Fixes issue #641 where users were getting banned due to rapid successive
Claude runs triggered by the synchronize event.
Changes:
- Add checkHumanActor call to agent mode's prepare() method to reject
bot-triggered workflows unless explicitly allowed via allowed_bots
- Update checkHumanActor to accept GitHubContext (union type) instead
of just ParsedGitHubContext
- Add tests for bot rejection/allowance in agent mode
Claude-Generated-By: Claude Code (cli/claude-opus-4-5=100%)
Claude-Steers: 1
Claude-Permission-Prompts: 3
Claude-Escapes: 0
Add a new section to security.md explaining that in the default
configuration, Claude commits to a branch and provides a link for
the user to create the PR themselves, ensuring human oversight.
Claude-Generated-By: Claude Code (cli/claude-opus-4-5=100%)
Claude-Steers: 2
Claude-Permission-Prompts: 2
Claude-Escapes: 0
Co-authored-by: Claude <noreply@anthropic.com>
* fix: use original title from webhook payload instead of fetched title
- Add extractOriginalTitle() helper to extract title from webhook payload
- Add originalTitle parameter to fetchGitHubData()
- Update tag mode to pass original title from webhook context
- Add tests for extractOriginalTitle and originalTitle parameter
This ensures the title used in prompts is the one that existed when the
trigger event occurred, rather than a potentially modified title fetched
later via GraphQL.
* fix: add title sanitization and explicit TOCTOU test
- Apply sanitizeContent() to titles in formatContext() for defense-in-depth
- Add explicit test documenting TOCTOU prevention for title handling
Previously, the SDK path would result in the CLI setting the entrypoint
to 'sdk-ts' internally, while the non-SDK (CLI) path would correctly
set it to 'claude-code-github-action' based on the CLAUDE_CODE_ACTION
env var.
This change explicitly sets CLAUDE_CODE_ENTRYPOINT in both:
1. The action.yml env block (for consistency)
2. The SDK options env (to override the CLI's internal default)
The CLI respects pre-set entrypoint values, so this ensures consistent
user agent reporting for both execution paths.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* fix: prevent orphaned installer processes from blocking retries
When the `timeout` command expires during Claude Code installation, it only
kills the direct child bash process, not the grandchild installer processes.
These orphaned processes continue holding a lock file, causing retry attempts
to fail with "another process is currently installing Claude".
Add `--foreground` flag to run the command in a foreground process group so
all child processes are killed on timeout. Add `--kill-after=10` to send
SIGKILL if SIGTERM doesn't terminate processes within 10 seconds.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: apply same timeout fix to root action.yml
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: send user request as separate content block for slash command support
When in tag mode with the SDK path, extracts the user's request from the
trigger comment (text after @claude) and sends it as a separate content
block. This enables the CLI to process slash commands like "/review-pr".
- Add extract-user-request utility to parse trigger comments
- Write user request to separate file during prompt generation
- Send multi-block SDKUserMessage when user request file exists
- Add tests for the extraction utility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: address PR feedback
- Fix potential ReDoS vulnerability by using string operations instead of regex
- Remove unused extractUserRequestFromEvent function and tests
- Extract USER_REQUEST_FILENAME to shared constants
- Conditionally log user request based on showFullOutput setting
- Add JSDoc documentation to extractUserRequestFromContext
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add ssh_signing_key input for SSH commit signing
Add a new ssh_signing_key input that allows passing an SSH signing key
for commit signing, as an alternative to the existing use_commit_signing
(which uses GitHub API-based commits).
When ssh_signing_key is provided:
- Git is configured to use SSH signing (gpg.format=ssh, commit.gpgsign=true)
- The key is written to ~/.ssh/claude_signing_key with 0600 permissions
- Git CLI commands are used (not MCP file ops)
- The key is cleaned up in a post step for security
Behavior matrix:
| ssh_signing_key | use_commit_signing | Result |
|-----------------|-------------------|--------|
| not set | false | Regular git, no signing |
| not set | true | GitHub API (MCP), verified commits |
| set | false | Git CLI with SSH signing |
| set | true | Git CLI with SSH signing (ssh_signing_key takes precedence)
* docs: add SSH signing key documentation
- Update security.md with detailed setup instructions for both signing options
- Explain that ssh_signing_key enables full git CLI operations (rebasing, etc.)
- Add ssh_signing_key to inputs table in usage.md
- Update bot_id/bot_name descriptions to note they're needed for verified commits
* fix: address security review feedback for SSH signing
- Write SSH key atomically with mode 0o600 (fixes TOCTOU race condition)
- Create .ssh directory with mode 0o700 (SSH best practices)
- Add input validation for SSH key format
- Remove unused chmod import
- Add tests for validation logic
Update the AWS Bedrock documentation link to point to the new
code.claude.com domain.
Fixes#756
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
The gh CLI prefers GH_TOKEN over GITHUB_TOKEN. When a calling workflow
sets GH_TOKEN in env, the action's GITHUB_TOKEN was being ignored,
causing the gh CLI to use the wrong token (e.g., the default workflow
token instead of an App token).
This ensures Claude's gh CLI commands use the action's prepared token.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
When users specify --setting-sources in claude_args (e.g., '--setting-sources user'),
the action now respects that value instead of overriding it with all three sources.
This fixes an issue where users who wanted to avoid in-repo configs would still
have them loaded because the settingSources was hardcoded to ['user', 'project', 'local'].
Fixes#749
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
* fix: merge multiple --mcp-config flags instead of overwriting
When users provide their own --mcp-config in claude_args, the action's
built-in MCP servers (github_comment, github_ci, etc.) were being lost
because multiple --mcp-config flags were overwriting each other.
This fix:
- Adds mcp-config to ACCUMULATING_FLAGS to collect all values
- Changes delimiter to null character to avoid conflicts with JSON
- Adds mergeMcpConfigs() to combine mcpServers objects from multiple configs
- Merges inline JSON configs while preserving file path configs
Fixes#745🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
* fix: support hyphenated --allowed-tools flag and multiple values
The --allowed-tools flag was not being parsed correctly when:
1. Using the hyphenated form (--allowed-tools) instead of camelCase (--allowedTools)
2. Passing multiple space-separated values after a single flag
(e.g., --allowed-tools "Tool1" "Tool2" "Tool3")
This fix:
- Adds hyphenated variants (allowed-tools, disallowed-tools) to ACCUMULATING_FLAGS
- Updates parsing to consume all consecutive non-flag values for accumulating flags
- Merges values from both camelCase and hyphenated variants
Fixes#746🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
Change USE_AGENT_SDK to default to true instead of false. The Agent SDK
path is now used by default; set USE_AGENT_SDK=false to use the CLI path.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Two fixes for the Agent SDK path (USE_AGENT_SDK=true):
1. Add settingSources to load filesystem settings
- Without this, CLI-installed plugins aren't available to the SDK
- Also needed to load CLAUDE.md files from the project
2. Default systemPrompt to claude_code preset
- Without an explicit systemPrompt, the SDK would use no system prompt
- Now defaults to { type: "preset", preset: "claude_code" } to match CLI behavior
Also adds logging of SDK options (excluding env) for debugging.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* fix: merge allowedTools from claudeArgs when using Agent SDK
When USE_AGENT_SDK=true, the allowedTools from claudeArgs (which contains
tag mode's required tools like mcp__github_comment__update_claude_comment)
were being lost because parseClaudeArgsToExtraArgs converts args to a
Record<string, string>, and the SDK was using sdkOptions.allowedTools
(from direct options) instead of merging with extraArgs.allowedTools.
This fix:
- Extracts allowedTools/disallowedTools from extraArgs after parsing
- Merges them with any direct options.allowedTools/disallowedTools
- Removes them from extraArgs to prevent duplicate CLI flags
- Passes the merged list as sdkOptions.allowedTools
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: accumulate multiple --allowedTools flags in claudeArgs
When tag mode adds its --allowedTools (with MCP tools) and the user also
provides --allowedTools in their claude_args, the parseClaudeArgsToExtraArgs
function was only keeping the last value. This caused tag mode's required
tools like mcp__github_comment__update_claude_comment to be lost.
Now allowedTools and disallowedTools flags accumulate their values when
they appear multiple times in claudeArgs, so both tag mode's tools and
user's tools are preserved.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Adds a shorter, more concise prompt for tag mode that trusts the model
to figure out details. Opt-in via USE_SIMPLE_PROMPT=true. The simplified
prompt keeps all context data but reduces instructions from ~250 to ~70 lines.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add Agent SDK support with USE_AGENT_SDK feature flag
Add a feature-flagged code path that uses the Agent SDK instead of
spawning the CLI as a subprocess. When USE_AGENT_SDK=true is set,
the new SDK path is used; otherwise, existing CLI behavior is unchanged.
Changes:
- Add parse-sdk-options.ts for parsing ClaudeOptions into SDK format
- Add run-claude-sdk.ts for SDK execution with query() function
- Update run-claude.ts with feature flag check at entry point
- Update update-comment-link.ts to handle both cost_usd and total_cost_usd
- Add @anthropic-ai/claude-agent-sdk dependency
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: simplify SDK types by using @anthropic-ai/claude-agent-sdk types directly
- Remove duplicate SdkRunOptions and McpStdioServerConfig types
- Use SDK's Options and McpStdioServerConfig types directly
- Return { sdkOptions, showFullOutput, hasJsonSchema } from parseSdkOptions
- Remove unnecessary convertMcpServers function
- Net reduction of ~70 lines
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: use extraArgs for claudeArgs pass-through to CLI
Simplify option parsing by converting claudeArgs to extraArgs record
and letting the SDK/CLI handle --mcp-config, --json-schema, etc.
- Remove extractJsonSchema and parseMcpConfigs functions
- Add parseClaudeArgsToExtraArgs for simple flag parsing
- CLI handles complex args like --mcp-config directly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* ci
* refactor: remove hardcoded permission bypass flags
The SDK path should match CLI path behavior - permissions are handled
by the CLI itself, not hardcoded in the action.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: add logging for SDK vs CLI path selection
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add trigger-time validation for issue/PR body content to prevent attackers
from exploiting a race condition where they edit the body between when an
authorized user triggers @claude and when Claude processes the request.
The existing filterCommentsToTriggerTime() already protected comments -
this extends the same pattern to the main issue/PR body via isBodySafeToUse().
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
The GNU `timeout` command is not available on macOS. Check if it exists
and use it when available, otherwise run without timeout.
Also extracts the version into a CLAUDE_CODE_VERSION variable for
easier maintenance.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* chore: remove experimental allowed domains feature
Remove the experimental_allowed_domains feature which was used to
restrict network access via a Squid proxy. This removes:
- The input definition from action.yml
- The Network Restrictions workflow step
- The setup-network-restrictions.sh script
- Documentation from experimental.md, usage.md, and related files
- The input default from collect-inputs.ts
* chore: fix formatting with prettier
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
* feat: add Azure AI Foundry provider support
Add support for Azure AI Foundry as a fourth cloud provider option alongside Anthropic API, AWS Bedrock, and Google Vertex AI.
Changes:
- Add use_foundry input to enable Azure AI Foundry authentication
- Add Azure environment variables (ANTHROPIC_FOUNDRY_RESOURCE, ANTHROPIC_FOUNDRY_API_KEY, ANTHROPIC_FOUNDRY_BASE_URL)
- Support automatic base URL construction from resource name
- Add validation logic with mutual exclusivity checks for all providers
- Add comprehensive test coverage (7 Azure-specific tests, 3 mutual exclusivity tests)
- Add complete Azure AI Foundry documentation with OIDC and API key authentication
- Update README to reference Azure AI Foundry support
Features:
- Primary authentication via Microsoft Entra ID (OIDC) using azure/login action
- Optional API key authentication fallback
- Custom model deployment name support via ANTHROPIC_DEFAULT_*_MODEL variables
- Clear validation error messages for missing configuration
All tests pass (25 validation tests total).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: rename Azure AI Foundry to Microsoft Foundry and remove API key support
- Rename all references from "Azure AI Foundry" to "Microsoft Foundry"
- Remove ANTHROPIC_FOUNDRY_API_KEY support (OIDC only)
- Update documentation to reflect OIDC-only authentication
- Update tests to remove API key test case
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: simplify Microsoft Foundry setup and remove URL auto-construction
- Link to official docs instead of duplicating setup instructions
- Remove automatic base URL construction from resource name
- Pass ANTHROPIC_FOUNDRY_BASE_URL as-is
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Updates documentation examples to use @v1 instead of @beta in:
- docs/setup.md: custom GitHub app example
- docs/configuration.md: additional permissions examples
Migration guide and usage comparison examples intentionally kept with @beta to show old syntax.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
- Added plugin_marketplaces input to both main and base-action action.yml files
- Updated install-plugins.ts to support multiple marketplace URLs (newline-separated)
- Added validation for marketplace URLs to prevent security issues
- Updated installPlugins function to dynamically add marketplaces instead of hardcoding
- Defaults to official Claude Code marketplace when no marketplaces are specified
- Updated base-action index.ts to pass plugin_marketplaces to installPlugins
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Clarifies which permissions are currently used (Contents, Pull Requests, Issues) versus those requested for planned future features (Discussions, Actions, Checks, Workflows).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* docs: add prompt injection security note
Add warning about potential hidden markdown in untrusted content from external contributors. Documents existing sanitization measures while acknowledging new bypass techniques may emerge.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Update docs/security.md
Co-authored-by: David Dworken <dworken@anthropic.com>
* format
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: David Dworken <dworken@anthropic.com>
Changed test prompts from communication-style echo commands to legitimate
technical operations. This ensures Claude attempts the Bash tool call
(which then gets blocked by permissions) instead of refusing based on
communication guidelines.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Add documentation for the two previously undocumented inputs that allow
users to provide custom executables for specialized environments:
- path_to_claude_code_executable: for custom Claude Code binaries
- path_to_bun_executable: for custom Bun runtime
These inputs are particularly useful for environments like Nix, NixOS,
custom containers, and other package management systems where the
default installation may not work.
Updated files:
- docs/usage.md: Added to inputs table
- docs/faq.md: Added FAQ entry with examples and use cases
- docs/configuration.md: Added dedicated section with examples
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Added a PostToolUse hook that automatically runs `bun run format` after
Edit, Write, or MultiEdit operations, similar to the Python SDK's ruff
formatting hook. This ensures code is automatically formatted whenever
changes are made.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* enable track_progress for comments
* refactor: pass mode explicitly to prepareMcpConfig
Update prepareMcpConfig to receive the mode parameter from its callers
instead of detecting agent mode by checking context.inputs.prompt.
This makes mode determination explicit and controlled by the caller.
Also update all test cases to include the required mode parameter
and fix agent mode test expectations to match new behavior where
MCP config is only included when tools are explicitly allowed.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix test
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: update claude-review workflow to use progress tracking and slash command
- Rename workflow from "Auto review PRs" to "PR Review with Progress Tracking"
- Update trigger types to include synchronize, ready_for_review, reopened
- Add pull-requests: write permission for tracking comments
- Replace direct_prompt with /review-pr slash command using custom command file
- Update to use claude-code-action@v1
- Switch to inline comment tool for more precise PR feedback
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* agents
* refactor: standardize agent output format instructions
Unified the output format instructions across all reviewer agents to follow a consistent structure:
- Converted numbered sections to bold headers for better readability
- Standardized "Review Structure" sections across all agents
- Maintained distinct analysis areas specific to each reviewer type
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
The GitHub comment MCP server was being included in agent mode even when no comment tools were explicitly allowed. This fix ensures the server is only included in tag mode where it's always needed for updating Claude comments.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Removes the OIDC id-token permission requirement and adds explicit github_token input to both workflow files. This simplifies authentication by using the standard GITHUB_TOKEN instead of requiring OIDC token exchange.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Add id-token write permission for OIDC token exchange
- Update prompt to emphasize adding P1/P2/P3 priority labels based on label descriptions
- Ensure Claude selects appropriate priority labels from the available options
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Adds a new optional bot_id input parameter that defaults to the github-actions[bot] ID (41898282). This resolves the "403 Resource not accessible by integration" error that occurs when using GitHub App installation tokens, which cannot access the /user endpoint.
Changes:
- Add bot_id input to action.yml with default value
- Update context parsing to include bot_id from environment
- Modify agent mode to use bot_id when available, avoiding API calls that fail with GitHub App tokens
- Add clear error handling for GitHub App token limitations
- Update documentation in usage.md and faq.md
- Fix test mocks to include bot_id field
This allows users to specify a custom bot user ID or use the default github-actions[bot] ID automatically, preventing 403 errors in automation workflows.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Changed from @anthropics/claude-code-base-action to @anthropics/claude-code-action
to use the correct action name in the issue triage workflow.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Add documentation for the timeout_minutes input removal that occurred in PR #482.
The input has been replaced with standard GitHub Actions timeout-minutes at job level.
Fixes#527
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bhat <ashwin-ant@users.noreply.github.com>
Implement time-based filtering for GitHub comments and reviews to prevent
malicious actors from editing existing comments after Claude is triggered
to inject harmful content.
Changes:
- Add updatedAt and lastEditedAt fields to GraphQL queries
- Update GitHubComment and GitHubReview types with timestamp fields
- Implement filterCommentsToTriggerTime() and filterReviewsToTriggerTime()
- Add extractTriggerTimestamp() to extract trigger time from webhooks
- Update tag and review modes to pass trigger timestamp to data fetcher
Security benefits:
- Prevents comment injection attacks via post-trigger edits
- Maintains chronological integrity of conversation context
- Ensures only comments in their final state before trigger are processed
- Backward compatible with graceful degradation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Add PR repository and number to review prompts
- Note that PR branch is already checked out
- Update allowed tools to use inline comments and gh CLI
- Remove experimental review mode example in favor of standardized approach
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Always create a new object copy of defaultInputs to prevent mutations from affecting other tests.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Commenting out the GitHub release creation step for the base action repository
to temporarily pause automatic releases while keeping tag synchronization active.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* tmp
* chore: migrate GitHub workflows from @beta to @v1
- Update claude.yml and issue-triage.yml to use claude-code-action@v1
- Migrate deprecated inputs to new claude_args format
- Move mcp_config to --mcp-config in claude_args
- Follow v1 migration guide for simplified configuration
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Remove mcp_config input in favor of --mcp-config in claude_args
BREAKING CHANGE: The mcp_config input has been removed. Users should now use --mcp-config flag in claude_args instead.
This simplifies the action's input surface area and aligns better with the Claude Code CLI interface. Users can still add multiple MCP configurations by using multiple --mcp-config flags.
Migration:
- Before: mcp_config: '{"mcpServers": {...}}'
- After: claude_args: '--mcp-config {"mcpServers": {...}}'
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add outer action MCP tests to workflow
- Add test-outer-action-inline-mcp job to test inline MCP config via claude_args
- Add test-outer-action-file-mcp job to test file-based MCP config via claude_args
- Keep base-action tests unchanged (they still use mcp_config parameter)
- Test that MCP tools are properly discovered and can be executed through the outer action
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix: Add Bun setup to outer action MCP test jobs
The test jobs for the outer action were failing because Bun wasn't installed.
Added Setup Bun step to both test-outer-action-inline-mcp and test-outer-action-file-mcp jobs.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add id-token permission to outer action MCP test jobs
The outer action needs id-token: write permission for OIDC authentication
when using the GitHub App. Added full permissions block to both
test-outer-action-inline-mcp and test-outer-action-file-mcp jobs.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Use github_token parameter instead of id-token permission
Replace id-token: write permission with explicit github_token parameter
for both outer action MCP test jobs. This simplifies authentication by
using the provided GitHub token directly.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Use RUNNER_TEMP environment variable consistently
Changed from GitHub Actions expression syntax to environment variable
for consistency with the rest of the workflow file.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Use execution_file output from action instead of hardcoded path
Updated outer action test jobs to:
- Add step IDs (claude-inline-test, claude-file-test)
- Use the execution_file output from the action steps
- This is more reliable than hardcoding the output file path
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* tmp
* Fix MCP test assertions to match actual output format
Updated the test assertions to match the actual JSON structure:
- Tool calls are in assistant messages with type='tool_use'
- Tool results are in user messages with type='tool_result'
- The test tool returns 'Test tool response' not 'Hello from test tool'
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Make inline MCP test actually use the tool instead of just listing
Changed the inline MCP test to:
- Request that Claude uses the test tool (not just list it)
- Add --allowedTools to ensure the tool can be used
- Check that the tool was actually called and returned expected result
- Output the full JSON for debugging
This makes both tests (inline and file-based) consistent in their approach.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Remove the update-beta-tag job since the update-major-tag job already handles major version tagging (v0, v1, v2). Keep release marked as non-latest to allow v1 to remain the latest release.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add path_to_bun_executable input for custom Bun installations
Adds optional input to specify a custom Bun executable path, bypassing automatic installation. This enables:
- Using pre-installed Bun binaries for faster workflow runs
- Testing with specific Bun versions for debugging
- Custom installation paths in unique environments
Follows the same pattern as path_to_claude_code_executable input.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: consolidate custom executable tests into single workflow
- Remove separate test-custom-executable.yml workflow
- Rename test-custom-bun.yml to test-custom-executables.yml
- Add comprehensive tests for custom Claude, custom Bun, and both together
- Improve verification steps with better error handling
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* simplify: test workflow to single job testing both custom executables
- Remove individual test jobs for Claude and Bun
- Keep only the combined test that validates both custom executables work together
- Simplifies CI workflow and reduces redundant testing
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add path_to_claude_code_executable input for custom Claude Code installations
Adds optional input to specify a custom Claude Code executable path, bypassing automatic installation. This enables:
- Using pre-installed Claude Code binaries
- Testing with specific versions for debugging
- Custom installation paths in unique environments
Includes warning that older versions may cause compatibility issues with new features.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* test: add workflow to test custom Claude Code executable path
Adds test workflow that:
- Manually installs Claude Code via install script
- Uses the new path_to_claude_code_executable input
- Verifies the custom executable path works correctly
- Validates output and execution success
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Fixes "stdout maxBuffer length exceeded" error by increasing the buffer
from Node.js default of 1MB to 10MB when processing Claude output with jq.
This prevents failures when Claude produces large execution logs.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Update the workflow validation message to be more specific about when
Claude Code workflows will start working, providing clearer guidance
to users experiencing this validation error.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
When running tests locally, process.env.RUNNER_TEMP is undefined, causing
the code to literally create "undefined/claude-prompts/" directories in
the working directory. Added fallback to "/tmp" following the pattern
already used in src/mcp/github-actions-server.ts.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: skip action gracefully for workflow validation errors
Handle workflow_not_found_on_default_branch and workflow_content_mismatch
errors by skipping the action with a warning instead of failing. This
improves user experience when adding Claude Code workflows to new
repositories or making workflow changes in PRs.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Update src/github/token.ts
---------
Co-authored-by: Claude <noreply@anthropic.com>
