@nevzatcirak/review-mcp 2.6.0 → 2.7.0-rc.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +11 -8
  2. package/package.json +7 -7
package/README.md CHANGED
@@ -12,7 +12,7 @@ mode), are never logged and are never persisted. There is no telemetry and there
12
12
  are no embedded defaults for URLs or endpoints: everything comes from your
13
13
  configuration.
14
14
 
15
- **Status: stable (2.4.0).** Stable releases are published under the npm
15
+ **Status: stable (2.6.0).** Stable releases are published under the npm
16
16
  dist-tag `latest`; release candidates of the next version under `next`. See the
17
17
  [changelog](CHANGELOG.md).
18
18
 
@@ -22,7 +22,7 @@ dist-tag `latest`; release candidates of the next version under `next`. See the
22
22
  ([Setup guide, steps 2 and 3](docs/setup.md#2-create-tokens)). A read-only
23
23
  token is enough for reviews and questions that are not published.
24
24
  2. Register the server with your client. With npm there is nothing to install.
25
- Pin the exact version (for example `@nevzatcirak/review-mcp@2.4.0`) so that
25
+ Pin the exact version (for example `@nevzatcirak/review-mcp@2.6.0`) so that
26
26
  `npx` does not reuse an older cached copy; update the pin to upgrade.
27
27
 
28
28
  **Claude Code**
@@ -34,7 +34,7 @@ dist-tag `latest`; release candidates of the next version under `next`. See the
34
34
  --env REVIEW_MCP_GITEA_BASE_URL=https://your-gitea.example \
35
35
  --env REVIEW_MCP_LLM_API_KEY="$REVIEW_MCP_LLM_API_KEY" \
36
36
  --env REVIEW_MCP_GITEA_TOKEN="$REVIEW_MCP_GITEA_TOKEN" \
37
- -- npx -y @nevzatcirak/review-mcp@2.4.0
37
+ -- npx -y @nevzatcirak/review-mcp@2.6.0
38
38
  ```
39
39
 
40
40
  **opencode** (`opencode.json`)
@@ -45,7 +45,7 @@ dist-tag `latest`; release candidates of the next version under `next`. See the
45
45
  "mcp": {
46
46
  "review-mcp": {
47
47
  "type": "local",
48
- "command": ["npx", "-y", "@nevzatcirak/review-mcp@2.4.0"],
48
+ "command": ["npx", "-y", "@nevzatcirak/review-mcp@2.6.0"],
49
49
  "enabled": true,
50
50
  "environment": {
51
51
  "REVIEW_MCP_LLM_BASE_URL": "https://llm.example.com/v1",
@@ -201,7 +201,8 @@ diag cache [--prune]` lists and sweeps the cache.
201
201
  ## Tools
202
202
 
203
203
  The server has ten tools in stdio mode and nine in `serve` mode (everything
204
- except `job_result`).
204
+ except `job_result`). With `decision.enabled` (stdio only) it has one more,
205
+ `pr_review_decision`.
205
206
 
206
207
  | Tool | What it does |
207
208
  |---|---|
@@ -210,12 +211,13 @@ except `job_result`).
210
211
  | `pr_info` | Which branch a pull request merges into and who has reviewed or approved it: human reviewers with their states, approval counts, required approvals and merge status where the provider exposes them. review-mcp's own reviews and comments are reported separately and never count as approvals. Also reports the CI results of the head commit (`ci`: state, counts and the failing checks), read from the provider; nothing is built or run. With `related` (up to four pull request URLs) it also reports their title, state, draft flag, target branch and head, without reading their diffs. Read-only, no LLM call; see [Pull request status](docs/pr-info.md). |
211
212
  | `pr_comment_reply` | Replies to a pull request comment (inside the thread on Bitbucket Server and GitLab, and on GitHub for an inline comment; as a quoting PR-level comment on Gitea, and on GitHub for a general comment). |
212
213
  | `pr_comment_create` | Posts a new comment on a pull request, PR-level or on a changed line (`file` and `line`). A line outside the diff is refused, never posted at PR level instead. |
213
- | `pr_review` | Reviews a pull request with your LLM. The title, description, existing comments and diff are sent to your LLM endpoint. Optionally publishes the review: one overview comment, edited in place on later runs, and inline comments on the changed lines. The model is also given the head commit's CI results (failing and pending checks, and a CI line in the overview), the project's guidelines file (`.review-mcp/guidelines.md`, else `CONTRIBUTING.md`) and a listing of the directories the change touches, both read at the target branch so a pull request cannot rewrite its own rules. `focus` (`security`, `architecture`, `performance`, `ux`, `tests`, `docs` or free text) reviews one area and never publishes; the findings of several focused reviews are merged by the client and published once with `findings` and `publish=true`, without another model call (the `multi_perspective_review` prompt describes the steps). With `incremental=true` (or `review.incremental`) it reviews only the files whose content changed since the last review it published, and lists the earlier findings the overview held without an inline comment on files that did not change; nothing changed means no model call and nothing posted. See [Reviewing pull requests](docs/review.md#incremental-review). It also checks the pull request against the issue it implements (requirements met, not met, needing human verification, and a verdict): an issue the pull request names on its own host, or one the client passes as `issue_context`, for example from a tracker MCP server; review-mcp never contacts trackers itself. See [Issue compliance](docs/review.md#issue-compliance). With `related` (up to four pull request URLs on any configured provider, each read with its own provider's token) it reviews the pull request together with the ones it belongs to, read as context only and never published to: their diffs are budgeted (`related.max_tokens`, contract files first), and mismatches between the pull requests, rollout compatibility and merge order are reported, with a finding in a related pull request listed in the overview with a link. See [Related pull requests](docs/review.md#related-pull-requests-and-repositories). |
214
+ | `pr_review_decision` | Records the token user's own decision on a pull request: `approve`, `request_changes` or `clear` (take your decision back; not on every host). No LLM call, and never derived from findings. Off by default: it is registered only with `decision.enabled`, and `decision.allowed` limits which decisions it may make. The `head_sha` you reviewed is required; a moved head, a pull request that is not open, and your own pull request are refused before anything is written. stdio only; see [Review decision](docs/decision.md). |
215
+ | `pr_review` | Reviews a pull request with your LLM. The title, description, existing comments and diff are sent to your LLM endpoint. Optionally publishes the review: one overview comment, edited in place on later runs, and inline comments on the changed lines. The model is also given the head commit's CI results (failing and pending checks, and a CI line in the overview), the project's guidelines file (`.review-mcp/guidelines.md`, else `CONTRIBUTING.md`) and a listing of the directories the change touches, both read at the target branch so a pull request cannot rewrite its own rules. `focus` (`security`, `architecture`, `performance`, `ux`, `tests`, `docs` or free text) reviews one area and never publishes; the findings of several focused reviews are merged by the client and published once with `findings` and `publish=true`, without another model call (the `multi_perspective_review` prompt describes the steps). With `incremental=true` (or `review.incremental`) it reviews only the files whose content changed since the last review it published, and lists the earlier findings the overview held without an inline comment on files that did not change; nothing changed means no model call and nothing posted. See [Reviewing pull requests](docs/review.md#incremental-review). It also checks the pull request against the issue it implements (requirements met, not met, needing human verification, and a verdict): an issue the pull request names on its own host, or one the client passes as `issue_context`, for example from a tracker MCP server; review-mcp never contacts trackers itself. See [Issue compliance](docs/review.md#issue-compliance). With `related` (up to four pull request URLs on any configured provider, each read with its own provider's token) it reviews the pull request together with the ones it belongs to, read as context only and never published to: their diffs are budgeted (`related.max_tokens`, contract files first), and mismatches between the pull requests, rollout compatibility and merge order are reported, with a finding in a related pull request listed in the overview with a link. `related` also takes repository URLs (stdio, with repository context on): the repository is read at one pinned commit and searched for uses of what the diff removes or changes (consumer impact), and a search without hits says so honestly, never "no impact". See [Related pull requests](docs/review.md#related-pull-requests-and-repositories). |
214
216
  | `pr_ask` | Answers a free-text question about a pull request, grounded in its title, description and diff. Takes `related` pull requests as context, as `pr_review` does. Optionally publishes the question and answer as a PR comment. |
215
217
  | `pr_describe` | Describes a pull request with your LLM: a title, the change types, a short summary and a walkthrough of the changed files. The title, description, branch names, commit messages and diff are sent to your LLM endpoint. By default it only reads; `publish=true` writes to the pull request, either one comment that later runs edit in place or a marked region at the end of the description (the author's text is never changed), and `update_title=true` also replaces the title. Files the model did not describe are listed, never padded in. The pull request's issue (or `issue_context`) is used as context, without a verdict. See [Describing pull requests](docs/describe.md). |
216
218
  | `pr_improve` | Suggests code changes for a pull request with your LLM: for each suggestion the existing and the improved code, a label and a score from 0 to 10 given by a second, self-review model call; suggestions below `improve.min_score` are dropped and counted, never silently lost. Each suggestion is checked against the head version of the file before it is called anchored; ones that cannot be are marked, not hidden. The title, description, branch names, existing comments and diff are sent to your LLM endpoint, with the project's guidelines file and the listing of the touched directories read at the target branch, as for `pr_review`. By default it only reads; `publish=true` writes to the pull request: one overview comment that later runs edit in place, and an inline comment on each verified suggestion that is on changed lines of one hunk (not repeated on later runs), with the change as a native suggestion block on GitHub and GitLab and as a diff block on Gitea and Bitbucket Server. See [Suggesting code changes](docs/improve.md). |
217
219
  | `job_result` | Returns the result of a `pr_review`, `pr_ask`, `pr_describe` or `pr_improve` call that took longer than `wait_seconds` and answered with a `job_id` instead. stdio only; see [Slow endpoints](docs/review.md#slow-endpoints). |
218
- | CI mode (`review-mcp ci`) | A command, not a tool: reviews, describes or suggests changes for the pull request of a pipeline (GitHub Actions, Gitea Actions, GitLab CI, or any CI with `--pr-url`), prints the result, posts it with `--publish`, and exits with a documented status (`--fail-on` for a gate). The tokens come from the pipeline's secrets as `REVIEW_MCP_*`; the code under review is never built or run. See [CI mode](docs/ci.md). |
220
+ | CI mode (`review-mcp ci`) | A command, not a tool: reviews, describes or suggests changes for the pull request of a pipeline (GitHub Actions, Gitea Actions, GitLab CI, or any CI with `--pr-url`), prints the result, posts it with `--publish`, and exits with a documented status (`--fail-on` for a gate). The tokens come from the pipeline's secrets as `REVIEW_MCP_*`; on GitHub Actions the job's own `GITHUB_TOKEN` is enough; the code under review is never built or run. See [CI mode](docs/ci.md). |
219
221
 
220
222
  The server also offers two MCP prompts:
221
223
 
@@ -235,10 +237,11 @@ The server also offers two MCP prompts:
235
237
  - [GitHub](docs/github.md): the token and its permissions, URL shapes and GitHub Enterprise Server, how the API address is derived, rate limits, the 3000-file and 250-commit limits, comment threads and why resolved state is not shown, replies and edits, one review per run, native suggestion blocks and their re-indentation rule, `pr_info` (approvals from rulesets and classic protection, the merge status), the description edit, repository context, and what is not supported.
236
238
  - [GitLab](docs/gitlab.md): the token and its scopes, URL shapes (nested groups, a context path), the minimum version 16.0, the diff base and the "diff not ready" case, the diff limits, rate limits, comment threads and replies, inline discussions and native suggestions, quick-action safety (what is sanitised, the diff fallback, the description refusal), `pr_info` (reviewers, approvals, the merge status), CI from commit statuses and what is not read, repository context, a proxy or `external_url` that differs from the base URL, and what is not supported.
237
239
  - [Pull request status](docs/pr-info.md): what `pr_info` reports (target branch, human reviewers, approvals, merge status, CI results, related pull requests), where each fact comes from, and why review-mcp's own reviews are not reviewers.
240
+ - [Review decision](docs/decision.md): `pr_review_decision` (off by default, stdio only): approve, request changes or clear as the token's user, the trust model (prompt injection, a moved head, bypassing review), `decision.enabled` and `decision.allowed`, the request each provider gets and the combinations it does not support, the body, the refusals in order, and why a pipeline should gate merges with `--fail-on` instead.
238
241
  - [Issue compliance](docs/review.md#issue-compliance): `pr_review` checks the pull request against its issue (met, not met, needs verification) from the provider's own issues or an `issue_context` the client fetches from any tracker; budgeted, fenced, never followed as instructions; [with a tracker MCP server](docs/setup.md#with-a-tracker-mcp-server).
239
242
  - [Repository config](docs/repo-config.md): a `.review-mcp.toml` in the reviewed repository, read at the target branch, tunes its reviews (language, ignore rules, guidelines paths, toggles, tighter caps, extra instructions, default focuses, documentation style) within an allow-list that never reaches hosts, models, limits or secrets.
240
243
  - [Repository context](docs/repo-context.md): opt-in, stdio only: shows the model where the symbols a pull request changes are used elsewhere in the project (a cached `git` fetch of the head, `git grep`, a budgeted prompt block) and, optionally, lets the model read the head commit itself (repository tools); its configuration, the cache, the security properties, the coverage line and the evaluation harness.
241
- - [CI mode](docs/ci.md): `review-mcp ci review|describe|improve` in a pipeline: the flags, the exit codes and `--fail-on`, how the pull request is detected, the tokens with their minimal rights, examples for GitHub Actions, Gitea Actions, GitLab CI and any other CI, incremental runs, the issue context file, and pull requests from forks.
244
+ - [CI mode](docs/ci.md): `review-mcp ci review|describe|improve` in a pipeline: the flags, the exit codes and `--fail-on`, how the pull request is detected, the tokens with their minimal rights, the job token's identity (`github.self_login`), examples for GitHub Actions, Gitea Actions, GitLab CI and any other CI, incremental runs, the issue context file, and pull requests from forks.
242
245
  - [Getting started](docs/getting-started.md): the minimal configuration and the diff budget in detail.
243
246
  - [Troubleshooting](docs/troubleshooting.md): the `diag` commands and every error sentence.
244
247
  - [Changelog](CHANGELOG.md).
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nevzatcirak/review-mcp",
3
- "version": "2.6.0",
3
+ "version": "2.7.0-rc.1",
4
4
  "description": "MCP server for AI-assisted pull-request review on Gitea and Bitbucket Server.",
5
5
  "keywords": [
6
6
  "mcp",
@@ -23,12 +23,12 @@
23
23
  "node": ">=18"
24
24
  },
25
25
  "optionalDependencies": {
26
- "@nevzatcirak/review-mcp-linux-x64": "2.6.0",
27
- "@nevzatcirak/review-mcp-linux-arm64": "2.6.0",
28
- "@nevzatcirak/review-mcp-darwin-x64": "2.6.0",
29
- "@nevzatcirak/review-mcp-darwin-arm64": "2.6.0",
30
- "@nevzatcirak/review-mcp-win32-x64": "2.6.0",
31
- "@nevzatcirak/review-mcp-win32-arm64": "2.6.0"
26
+ "@nevzatcirak/review-mcp-linux-x64": "2.7.0-rc.1",
27
+ "@nevzatcirak/review-mcp-linux-arm64": "2.7.0-rc.1",
28
+ "@nevzatcirak/review-mcp-darwin-x64": "2.7.0-rc.1",
29
+ "@nevzatcirak/review-mcp-darwin-arm64": "2.7.0-rc.1",
30
+ "@nevzatcirak/review-mcp-win32-x64": "2.7.0-rc.1",
31
+ "@nevzatcirak/review-mcp-win32-arm64": "2.7.0-rc.1"
32
32
  },
33
33
  "files": [
34
34
  "bin/review-mcp.js",