actions/claude-code-action
1
0
Fork 0
mirror of https://github.com/anthropics/claude-code-action.git synced 2026-08-22 03:18:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(inline-comment): add confirmed param + probe-pattern safety net (#1048)

Browse Source 
* feat(inline-comment): add confirmed param + probe-pattern safety net

Subagents that inherit this tool sometimes probe it with test comments
('Test comment to see if I can create inline comments') after hitting
unrelated errors elsewhere. Recurring issue across customer PRs.

Adds two defenses:
1. confirmed param: set true to post (final review comments should pass
   this). When false, buffers to a JSONL file instead of posting.
2. Probe-pattern safety net: when confirmed is omitted (backward compat
   for existing prompts), the body is checked against obvious probe
   patterns ('test comment', 'can i', 'does this work', etc.). Matching
   calls are buffered instead of posted.

A post-run step in action.yml reports the buffered call count and bodies
as a workflow warning for diagnostics.

Backward compatibility:
- Existing single-agent prompts (no confirmed param) post normally unless
  the body happens to start with a probe phrase (unlikely for real
  review comments)
- The code-review skill is being updated to pass confirmed: true in its
  final posting step
- Subagent probes that would previously post now harmlessly buffer

* refactor: replace probe-regex with Haiku classification in post-step

The regex approach was narrow and could miss creative probe phrasings.
Replaced with a batch Haiku classification that runs after the session
completes.

Flow:
- MCP server: confirmed !== true -> buffer to JSONL (no classification
  in-band, no latency in the tool path)
- Post-step (src/entrypoints/post-buffered-inline-comments.ts): reads
  buffer, sends all bodies to a single Haiku call, posts only those
  classified as real review comments
- confirmed=false entries are never posted regardless of classification

Fail-open: if ANTHROPIC_API_KEY is unavailable (Bedrock/Vertex users)
or the classification call fails, posts all unconfirmed comments. This
matches pre-PR behavior where all calls posted immediately.

The post-step emits ::warning:: for each filtered comment so users can
see what was dropped and why.

* feat: add classify_inline_comments opt-out input

New action input classify_inline_comments (default 'true'). Setting to
'false' restores pre-buffering behavior: all inline comment calls post
immediately regardless of the confirmed param.

Threads through: action input -> CLASSIFY_INLINE_COMMENTS env ->
context.inputs.classifyInlineComments -> MCP server env ->
CLASSIFY_ENABLED module const.

Post-step is also gated on the input so it skips entirely when
classification is disabled.

* docs: document classify_inline_comments input and confirmed param

- usage.md: add classify_inline_comments to inputs table
- solutions.md: mention confirmed=true in the prompt example and explain
  buffering/classification in the tool permissions section
This commit is contained in:
kashyap murali
2026-03-12 00:12:55 -07:00
committed by GitHub
parent 567be3da98
commit 5d0cc745cd
13 changed files with 354 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/solutions.md
+2 -2
View File
@@ -55,7 +55,7 @@ jobs:
Note: The PR branch is already checked out in the current working directory.
Use `gh pr comment` for top-level feedback.
Use `mcp__github_inline_comment__create_inline_comment` to highlight specific code issues.
Use `mcp__github_inline_comment__create_inline_comment` (with `confirmed: true`) to highlight specific code issues.
Only post GitHub comments - don't submit review text as messages.
claude_args: |
@@ -585,7 +585,7 @@ prompt: |
### Common Tool Permissions
- **PR Comments**: `Bash(gh pr comment:*)`
- **Inline Comments**: `mcp__github_inline_comment__create_inline_comment`
- **Inline Comments**: `mcp__github_inline_comment__create_inline_comment` — pass `confirmed: true` to post immediately. When omitted, the comment is buffered and classified after the session ends (real review comments post, test/probe comments are filtered). This prevents subagent test comments from reaching PRs. To disable classification entirely, set `classify_inline_comments: 'false'` on the action.
- **File Operations**: `Read,Write,Edit`
- **Git Operations**: `Bash(git:*)`
docs/usage.md
+30 -29
View File
@@ -52,35 +52,36 @@ jobs:
## Inputs
| Input | Description | Required | Default |
| -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------- |
| `anthropic_api_key` | Anthropic API key (required for direct API, not needed for Bedrock/Vertex) | No\* | - |
| `claude_code_oauth_token` | Claude Code OAuth token (alternative to anthropic_api_key) | No\* | - |
| `prompt` | Instructions for Claude. Can be a direct prompt or custom template for automation workflows | No | - |
| `track_progress` | Force tag mode with tracking comments. Only works with specific PR/issue events. Preserves GitHub context | No | `false` |
| `include_fix_links` | Include 'Fix this' links in PR code review feedback that open Claude Code with context to fix the identified issue | No | `true` |
| `claude_args` | Additional [arguments to pass directly to Claude CLI](https://docs.claude.com/en/docs/claude-code/cli-reference#cli-flags) (e.g., `--max-turns 10 --model claude-4-0-sonnet-20250805`) | No | "" |
| `base_branch` | The base branch to use for creating new branches (e.g., 'main', 'develop') | No | - |
| `use_sticky_comment` | Use just one comment to deliver PR comments (only applies for pull_request event workflows) | No | `false` |
| `github_token` | GitHub token for Claude to operate with. **Only include this if you're connecting a custom GitHub app of your own!** | No | - |
| `use_bedrock` | Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API | No | `false` |
| `use_vertex` | Use Google Vertex AI with OIDC authentication instead of direct Anthropic API | No | `false` |
| `assignee_trigger` | The assignee username that triggers the action (e.g. @claude). Only used for issue assignment | No | - |
| `label_trigger` | The label name that triggers the action when applied to an issue (e.g. "claude") | No | - |
| `trigger_phrase` | The trigger phrase to look for in comments, issue/PR bodies, and issue titles | No | `@claude` |
| `branch_prefix` | The prefix to use for Claude branches (defaults to 'claude/', use 'claude-' for dash format) | No | `claude/` |
| `settings` | Claude Code settings as JSON string or path to settings JSON file | No | "" |
| `additional_permissions` | Additional permissions to enable. Currently supports 'actions: read' for viewing workflow results | No | "" |
| `use_commit_signing` | Enable commit signing using GitHub's API. Simple but cannot perform complex git operations like rebasing. See [Security](./security.md#commit-signing) | No | `false` |
| `ssh_signing_key` | SSH private key for signing commits. Enables signed commits with full git CLI support (rebasing, etc.). See [Security](./security.md#commit-signing) | No | "" |
| `bot_id` | GitHub user ID to use for git operations (defaults to Claude's bot ID). Required with `ssh_signing_key` for verified commits | No | `41898282` |
| `bot_name` | GitHub username to use for git operations (defaults to Claude's bot name). Required with `ssh_signing_key` for verified commits | No | `claude[bot]` |
| `allowed_bots` | Comma-separated list of allowed bot usernames, or '\*' to allow all bots. Empty string (default) allows no bots. **⚠️ On public repos with `'*'`, external Apps may be able to invoke this action.** See [Security](./security.md) | No | "" |
| `allowed_non_write_users` | **⚠️ RISKY**: Comma-separated list of usernames to allow without write permissions, or '\*' for all users. Only works with `github_token` input. See [Security](./security.md) | No | "" |
| `path_to_claude_code_executable` | Optional path to a custom Claude Code executable. Skips automatic installation. Useful for Nix, custom containers, or specialized environments | No | "" |
| `path_to_bun_executable` | Optional path to a custom Bun executable. Skips automatic Bun installation. Useful for Nix, custom containers, or specialized environments | No | "" |
| `plugin_marketplaces` | Newline-separated list of Claude Code plugin marketplace Git URLs to install from (e.g., see example in workflow above). Marketplaces are added before plugin installation | No | "" |
| `plugins` | Newline-separated list of Claude Code plugin names to install (e.g., see example in workflow above). Plugins are installed before Claude Code execution | No | "" |
| Input | Description | Required | Default |
| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------------- |
| `anthropic_api_key` | Anthropic API key (required for direct API, not needed for Bedrock/Vertex) | No\* | - |
| `claude_code_oauth_token` | Claude Code OAuth token (alternative to anthropic_api_key) | No\* | - |
| `prompt` | Instructions for Claude. Can be a direct prompt or custom template for automation workflows | No | - |
| `track_progress` | Force tag mode with tracking comments. Only works with specific PR/issue events. Preserves GitHub context | No | `false` |
| `include_fix_links` | Include 'Fix this' links in PR code review feedback that open Claude Code with context to fix the identified issue | No | `true` |
| `claude_args` | Additional [arguments to pass directly to Claude CLI](https://docs.claude.com/en/docs/claude-code/cli-reference#cli-flags) (e.g., `--max-turns 10 --model claude-4-0-sonnet-20250805`) | No | "" |
| `base_branch` | The base branch to use for creating new branches (e.g., 'main', 'develop') | No | - |
| `use_sticky_comment` | Use just one comment to deliver PR comments (only applies for pull_request event workflows) | No | `false` |
| `classify_inline_comments` | Buffer inline comments without `confirmed: true` and classify them (real review vs test/probe) via Haiku before posting after the session ends. Prevents subagent test comments. Set `'false'` to post all inline comments immediately | No | `true` |
| `github_token` | GitHub token for Claude to operate with. **Only include this if you're connecting a custom GitHub app of your own!** | No | - |
| `use_bedrock` | Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API | No | `false` |
| `use_vertex` | Use Google Vertex AI with OIDC authentication instead of direct Anthropic API | No | `false` |
| `assignee_trigger` | The assignee username that triggers the action (e.g. @claude). Only used for issue assignment | No | - |
| `label_trigger` | The label name that triggers the action when applied to an issue (e.g. "claude") | No | - |
| `trigger_phrase` | The trigger phrase to look for in comments, issue/PR bodies, and issue titles | No | `@claude` |
| `branch_prefix` | The prefix to use for Claude branches (defaults to 'claude/', use 'claude-' for dash format) | No | `claude/` |
| `settings` | Claude Code settings as JSON string or path to settings JSON file | No | "" |
| `additional_permissions` | Additional permissions to enable. Currently supports 'actions: read' for viewing workflow results | No | "" |
| `use_commit_signing` | Enable commit signing using GitHub's API. Simple but cannot perform complex git operations like rebasing. See [Security](./security.md#commit-signing) | No | `false` |
| `ssh_signing_key` | SSH private key for signing commits. Enables signed commits with full git CLI support (rebasing, etc.). See [Security](./security.md#commit-signing) | No | "" |
| `bot_id` | GitHub user ID to use for git operations (defaults to Claude's bot ID). Required with `ssh_signing_key` for verified commits | No | `41898282` |
| `bot_name` | GitHub username to use for git operations (defaults to Claude's bot name). Required with `ssh_signing_key` for verified commits | No | `claude[bot]` |
| `allowed_bots` | Comma-separated list of allowed bot usernames, or '\*' to allow all bots. Empty string (default) allows no bots. **⚠️ On public repos with `'*'`, external Apps may be able to invoke this action.** See [Security](./security.md) | No | "" |
| `allowed_non_write_users` | **⚠️ RISKY**: Comma-separated list of usernames to allow without write permissions, or '\*' for all users. Only works with `github_token` input. See [Security](./security.md) | No | "" |
| `path_to_claude_code_executable` | Optional path to a custom Claude Code executable. Skips automatic installation. Useful for Nix, custom containers, or specialized environments | No | "" |
| `path_to_bun_executable` | Optional path to a custom Bun executable. Skips automatic Bun installation. Useful for Nix, custom containers, or specialized environments | No | "" |
| `plugin_marketplaces` | Newline-separated list of Claude Code plugin marketplace Git URLs to install from (e.g., see example in workflow above). Marketplaces are added before plugin installation | No | "" |
| `plugins` | Newline-separated list of Claude Code plugin names to install (e.g., see example in workflow above). Plugins are installed before Claude Code execution | No | "" |
### Deprecated Inputs