Compare commits
26 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c2595d0263 | |||
| d80d6a23a2 | |||
| a9c8ecfb0b | |||
| ec19622133 | |||
| e261976dd8 | |||
| 1c2292265b | |||
| b0dc6d0c09 | |||
| 2ac7f55396 | |||
| 177d56f218 | |||
| 55391c66d8 | |||
| 2287a8238c | |||
| 436e6a8824 | |||
| 687005d982 | |||
| 6a3c813279 | |||
| b8af8306a6 | |||
| 69e0a459c3 | |||
| 41c670b44b | |||
| 0d417e068e | |||
| aee903caa2 | |||
| 75190d53ed | |||
| 8b8462bdc8 | |||
| 565a077b01 | |||
| dab7871cb4 | |||
| 2adb23b3d9 | |||
| d9cacf6f62 | |||
| 67d835909f |
@@ -66,6 +66,14 @@ inputs:
|
||||
description: 'Print review to stdout instead of posting'
|
||||
required: false
|
||||
default: 'false'
|
||||
update-existing:
|
||||
description: 'Delete previous review from same bot after posting new one. Accepts: true/1/yes or false/0/no (default true)'
|
||||
required: false
|
||||
default: 'true'
|
||||
system-prompt-file:
|
||||
description: 'Local file with additional system prompt instructions (e.g. security review focus)'
|
||||
required: false
|
||||
default: ''
|
||||
|
||||
runs:
|
||||
using: 'composite'
|
||||
@@ -145,6 +153,8 @@ runs:
|
||||
LLM_TEMPERATURE: ${{ inputs.temperature }}
|
||||
LLM_TIMEOUT: ${{ inputs.timeout }}
|
||||
LLM_PROVIDER: ${{ inputs.llm-provider }}
|
||||
UPDATE_EXISTING: ${{ inputs.update-existing }}
|
||||
SYSTEM_PROMPT_FILE: ${{ inputs.system-prompt-file }}
|
||||
run: |
|
||||
ARGS=""
|
||||
if [ "${{ inputs.dry-run }}" = "true" ]; then
|
||||
|
||||
@@ -31,7 +31,11 @@ jobs:
|
||||
model: gpt-5
|
||||
- name: gpt
|
||||
token_secret: GPT_REVIEW_TOKEN
|
||||
model: gpt-5-mini
|
||||
model: gpt-4.1
|
||||
- name: security
|
||||
token_secret: SONNET_REVIEW_TOKEN
|
||||
model: gpt-5
|
||||
system_prompt_file: SECURITY_REVIEW.md
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-go@v5
|
||||
@@ -44,10 +48,13 @@ jobs:
|
||||
GITEA_REPO: ${{ github.repository }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
REVIEWER_TOKEN: ${{ secrets[matrix.token_secret] }}
|
||||
REVIEWER_NAME: ${{ matrix.name }}
|
||||
LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
|
||||
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
|
||||
LLM_MODEL: ${{ matrix.model }}
|
||||
CONVENTIONS_FILE: "CONVENTIONS.md"
|
||||
PATTERNS_REPO: "rodin/go-patterns"
|
||||
PATTERNS_FILES: "README.md,docs/"
|
||||
PATTERNS_FILES: "README.md,patterns/"
|
||||
LLM_TIMEOUT: "600"
|
||||
SYSTEM_PROMPT_FILE: ${{ matrix.system_prompt_file }}
|
||||
run: ./review-bot
|
||||
|
||||
@@ -1,17 +1,242 @@
|
||||
# review-bot
|
||||
|
||||
Automated code review bot for Gitea. Fetches a pull request diff, sends it to an LLM for analysis, and posts a structured review back to the PR.
|
||||
AI-powered code review bot for Gitea pull requests. Fetches diff + context, sends to an LLM, and posts a structured review (APPROVE / REQUEST_CHANGES) back to the PR.
|
||||
|
||||
## Features
|
||||
|
||||
- Fetches PR metadata, diff, and CI status from Gitea API
|
||||
- Sends context-rich prompts to any OpenAI-compatible LLM
|
||||
- Parses structured JSON review responses
|
||||
- Posts formatted reviews (APPROVE / REQUEST_CHANGES) back to Gitea
|
||||
- Supports custom coding conventions via repo files
|
||||
- Zero external dependencies — Go stdlib only
|
||||
- **Multi-provider**: OpenAI-compatible and Anthropic Messages API
|
||||
- **Context-aware**: Fetches full file content, conventions, language patterns, CI status
|
||||
- **Smart budget**: Automatically trims context to fit model token limits
|
||||
- **Idempotent reviews**: Posts new review, then cleans up stale ones (one review per bot)
|
||||
- **Custom prompts**: Load additional instructions from a file (e.g. security-focused review)
|
||||
- **Zero dependencies**: Go stdlib only
|
||||
|
||||
## Usage
|
||||
## Quick Start: Composite Action
|
||||
|
||||
The easiest way to use review-bot in your Gitea CI:
|
||||
|
||||
```yaml
|
||||
# .gitea/workflows/review.yml
|
||||
name: Review
|
||||
on:
|
||||
pull_request:
|
||||
types: [opened, synchronize]
|
||||
|
||||
jobs:
|
||||
review:
|
||||
runs-on: ubuntu-24.04
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: code-review
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: gpt-4.1
|
||||
```
|
||||
|
||||
That's it. Every PR gets an automated review.
|
||||
|
||||
## Examples
|
||||
|
||||
### Single reviewer with conventions
|
||||
|
||||
```yaml
|
||||
jobs:
|
||||
review:
|
||||
runs-on: ubuntu-24.04
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: reviewer
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: gpt-4.1
|
||||
conventions-file: CONVENTIONS.md
|
||||
timeout: '600'
|
||||
```
|
||||
|
||||
### Two reviewers with different models (diversity of opinion)
|
||||
|
||||
```yaml
|
||||
jobs:
|
||||
review:
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- name: gpt
|
||||
model: gpt-4.1
|
||||
token_secret: GPT_REVIEW_TOKEN
|
||||
- name: claude
|
||||
model: claude-sonnet-4-20250514
|
||||
token_secret: CLAUDE_REVIEW_TOKEN
|
||||
provider: anthropic
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets[matrix.token_secret] }}
|
||||
reviewer-name: ${{ matrix.name }}
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: ${{ matrix.model }}
|
||||
llm-provider: ${{ matrix.provider }}
|
||||
conventions-file: CONVENTIONS.md
|
||||
```
|
||||
|
||||
Each reviewer posts independently and only cleans up its own stale reviews.
|
||||
|
||||
### Multiple review types from a single bot account
|
||||
|
||||
Use the same Gitea token but different `reviewer-name` values to run specialized reviews without needing multiple bot accounts:
|
||||
|
||||
```yaml
|
||||
jobs:
|
||||
review:
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- name: code-quality
|
||||
model: gpt-4.1
|
||||
- name: security
|
||||
model: gpt-4.1
|
||||
system_prompt_file: .review/SECURITY.md
|
||||
- name: performance
|
||||
model: gpt-4.1
|
||||
system_prompt_file: .review/PERFORMANCE.md
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: ${{ matrix.name }}
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: ${{ matrix.model }}
|
||||
system-prompt-file: ${{ matrix.system_prompt_file }}
|
||||
```
|
||||
|
||||
The sentinel `<!-- review-bot:security -->` ensures the security review only replaces previous security reviews, never the code-quality or performance reviews.
|
||||
|
||||
### With language patterns from another repo
|
||||
|
||||
```yaml
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: reviewer
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: gpt-4.1
|
||||
conventions-file: CLAUDE.md
|
||||
patterns-repo: rodin/go-patterns,rodin/kubernetes-conventions
|
||||
patterns-files: "README.md,patterns/"
|
||||
```
|
||||
|
||||
Pattern repos are fetched at review time. The reviewer uses them as criteria for idiomatic code.
|
||||
|
||||
### Dry run (test without posting)
|
||||
|
||||
```yaml
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: test
|
||||
llm-base-url: ${{ secrets.LLM_BASE_URL }}
|
||||
llm-api-key: ${{ secrets.LLM_API_KEY }}
|
||||
llm-model: gpt-4.1
|
||||
dry-run: 'true'
|
||||
```
|
||||
|
||||
Prints the review to CI logs without posting to the PR. Useful for testing prompt changes.
|
||||
|
||||
### Using Anthropic directly
|
||||
|
||||
```yaml
|
||||
- uses: https://gitea.weiker.me/rodin/review-bot/.gitea/actions/review@v0.1.0
|
||||
with:
|
||||
reviewer-token: ${{ secrets.REVIEW_TOKEN }}
|
||||
reviewer-name: claude
|
||||
llm-base-url: https://api.anthropic.com
|
||||
llm-api-key: ${{ secrets.ANTHROPIC_API_KEY }}
|
||||
llm-model: claude-sonnet-4-20250514
|
||||
llm-provider: anthropic
|
||||
```
|
||||
|
||||
## Action Inputs
|
||||
|
||||
| Input | Required | Default | Description |
|
||||
|-------|----------|---------|-------------|
|
||||
| `reviewer-token` | Yes | — | Gitea token for posting reviews (needs `write:issue`, `write:repository`) |
|
||||
| `reviewer-name` | No | `""` | Logical identity for this reviewer. Used as sentinel for idempotent cleanup. Set this when running multiple review bots on the same PR. |
|
||||
| `llm-base-url` | Yes | — | LLM API base URL |
|
||||
| `llm-api-key` | Yes | — | LLM API key |
|
||||
| `llm-model` | Yes | — | Model name |
|
||||
| `llm-provider` | No | `openai` | API provider: `openai` or `anthropic` |
|
||||
| `conventions-file` | No | `""` | Path to coding conventions file in the repo |
|
||||
| `patterns-repo` | No | `""` | Comma-separated repos with language patterns (e.g. `rodin/go-patterns`) |
|
||||
| `patterns-files` | No | `README.md` | Files/directories to fetch from pattern repos |
|
||||
| `system-prompt-file` | No | `""` | Local file with additional system prompt instructions |
|
||||
| `temperature` | No | `0` | LLM temperature (0 = server default) |
|
||||
| `timeout` | No | `300` | LLM request timeout in seconds |
|
||||
| `dry-run` | No | `false` | Print review to stdout instead of posting |
|
||||
| `update-existing` | No | `true` | Delete previous review from same bot before posting. Accepts: true/1/yes or false/0/no |
|
||||
| `version` | No | `latest` | review-bot version to install |
|
||||
|
||||
## How Review Cleanup Works
|
||||
|
||||
When `reviewer-name` is set, the bot embeds a hidden sentinel in each review:
|
||||
|
||||
```html
|
||||
<!-- review-bot:code-review -->
|
||||
```
|
||||
|
||||
On the next run, it finds and deletes any review containing its own sentinel (except the one it just posted). This means:
|
||||
|
||||
- **One review per bot per PR** — no clutter from repeated pushes
|
||||
- **Multiple bots coexist** — each only cleans up its own reviews
|
||||
- **Same token, different roles** — a single bot account can post "code-review" and "security" reviews without conflict
|
||||
- **No extra permissions** — identity comes from the sentinel, not the API
|
||||
|
||||
If `reviewer-name` is empty, cleanup is skipped (reviews stack like before).
|
||||
|
||||
### Shared Token: Worst-Wins Behavior
|
||||
|
||||
When multiple review types share the same Gitea bot account (e.g. code-quality and security), Gitea determines the user's approval state from their **most recent review**. This creates a race condition: if security finds issues (REQUEST_CHANGES) but code-quality finishes last (APPROVE), the PR appears approved.
|
||||
|
||||
review-bot handles this automatically with **worst-wins reconciliation**: before posting, each job checks whether any sibling review from the same user already has REQUEST_CHANGES. If so and this job would post APPROVE, it posts as REQUEST_CHANGES instead — maintaining the block. This ensures the PR stays blocked until all checks pass, regardless of execution order.
|
||||
|
||||
**If you need independent approval/block per review type**, use separate Gitea bot accounts with their own tokens.
|
||||
|
||||
## Custom Review Prompts
|
||||
|
||||
Use `system-prompt-file` to specialize the review focus. The file contents are appended to the base system prompt as "Additional Review Instructions."
|
||||
|
||||
Example `SECURITY_REVIEW.md`:
|
||||
|
||||
```markdown
|
||||
You are performing a security-focused code review.
|
||||
|
||||
Focus areas:
|
||||
- Injection attacks (SQL, command, path traversal, template)
|
||||
- Authentication/Authorization (missing checks, privilege escalation)
|
||||
- Secrets exposure (hardcoded credentials, tokens in logs)
|
||||
- Input validation (unsanitized input, unsafe deserialization)
|
||||
- Race conditions (TOCTOU, unsynchronized shared state)
|
||||
|
||||
Rules:
|
||||
- Only report findings with security implications
|
||||
- Ignore style, naming, and general code quality
|
||||
- MAJOR = exploitable vulnerability, MINOR = hardening opportunity, NIT = theoretical risk
|
||||
- If no security-relevant changes exist, APPROVE with empty findings
|
||||
```
|
||||
|
||||
## CLI Usage
|
||||
|
||||
```bash
|
||||
review-bot \
|
||||
@@ -19,71 +244,74 @@ review-bot \
|
||||
--repo owner/name \
|
||||
--pr 42 \
|
||||
--reviewer-token "$GITEA_TOKEN" \
|
||||
--reviewer-name "code-review" \
|
||||
--llm-base-url https://api.openai.com/v1 \
|
||||
--llm-api-key "$OPENAI_API_KEY" \
|
||||
--llm-model gpt-4 \
|
||||
--reviewer-name "Sonnet" \
|
||||
--conventions-file CONVENTIONS.md \
|
||||
--dry-run
|
||||
--llm-model gpt-4.1 \
|
||||
--conventions-file CONVENTIONS.md
|
||||
```
|
||||
|
||||
## Environment Variables
|
||||
|
||||
All flags can be set via environment variables:
|
||||
All flags have environment variable equivalents:
|
||||
|
||||
| Flag | Env Var | Required | Description |
|
||||
|------|---------|----------|-------------|
|
||||
| `--gitea-url` | `GITEA_URL` | Yes | Gitea instance base URL |
|
||||
| `--repo` | `GITEA_REPO` | Yes | Repository in `owner/name` format |
|
||||
| `--pr` | `PR_NUMBER` | Yes | Pull request number |
|
||||
| `--reviewer-token` | `REVIEWER_TOKEN` | Yes | Gitea API token for posting reviews |
|
||||
| `--llm-base-url` | `LLM_BASE_URL` | Yes | OpenAI-compatible API base URL |
|
||||
| `--llm-api-key` | `LLM_API_KEY` | Yes | LLM API key |
|
||||
| `--llm-model` | `LLM_MODEL` | Yes | Model identifier |
|
||||
| `--reviewer-name` | `REVIEWER_NAME` | No | Display name in review footer |
|
||||
| `--conventions-file` | `CONVENTIONS_FILE` | No | Path to conventions file in repo |
|
||||
| `--dry-run` | — | No | Print review to stdout instead of posting |
|
||||
| Flag | Env Var |
|
||||
|------|---------|
|
||||
| `--gitea-url` | `GITEA_URL` |
|
||||
| `--repo` | `GITEA_REPO` |
|
||||
| `--pr` | `PR_NUMBER` |
|
||||
| `--reviewer-token` | `REVIEWER_TOKEN` |
|
||||
| `--reviewer-name` | `REVIEWER_NAME` |
|
||||
| `--llm-base-url` | `LLM_BASE_URL` |
|
||||
| `--llm-api-key` | `LLM_API_KEY` |
|
||||
| `--llm-model` | `LLM_MODEL` |
|
||||
| `--llm-provider` | `LLM_PROVIDER` |
|
||||
| `--conventions-file` | `CONVENTIONS_FILE` |
|
||||
| `--patterns-repo` | `PATTERNS_REPO` |
|
||||
| `--patterns-files` | `PATTERNS_FILES` |
|
||||
| `--system-prompt-file` | `SYSTEM_PROMPT_FILE` |
|
||||
| `--llm-temperature` | `LLM_TEMPERATURE` |
|
||||
| `--llm-timeout` | `LLM_TIMEOUT` |
|
||||
| `--update-existing` | `UPDATE_EXISTING` |
|
||||
|
||||
## Adding to a Gitea Repository
|
||||
## Setup
|
||||
|
||||
1. Build the binary or use the CI workflow approach (build in CI).
|
||||
1. **Create a Gitea bot account** (e.g. `review-bot`)
|
||||
2. **Generate a token** with scopes: `write:issue`, `write:repository`
|
||||
3. **Add secrets** to your Gitea repo (Settings → Actions → Secrets):
|
||||
- `REVIEW_TOKEN` — the bot's Gitea token
|
||||
- `LLM_BASE_URL` — your LLM endpoint
|
||||
- `LLM_API_KEY` — your LLM key
|
||||
4. **Add the workflow** (see Quick Start above)
|
||||
|
||||
2. Add secrets to your Gitea repo (Settings → Actions → Secrets):
|
||||
- `SONNET_REVIEW_TOKEN` — Gitea token for the Sonnet reviewer account
|
||||
- `GPT_REVIEW_TOKEN` — Gitea token for the GPT reviewer account
|
||||
- `LLM_BASE_URL` — Your LLM API endpoint
|
||||
- `LLM_API_KEY` — Your LLM API key
|
||||
### Token Scopes Required
|
||||
|
||||
3. Copy `.gitea/workflows/ci.yml` to your repo (or adapt it).
|
||||
| Scope | Purpose |
|
||||
|-------|---------|
|
||||
| `write:issue` | Post and delete reviews |
|
||||
| `write:repository` | Read PR diffs, file content, commit statuses |
|
||||
|
||||
4. On every PR, the bot will:
|
||||
- Run tests and vet
|
||||
- Build review-bot
|
||||
- Post reviews from each configured LLM reviewer
|
||||
No `read:user` scope needed — the bot identifies itself from the review response.
|
||||
|
||||
## Development
|
||||
|
||||
```bash
|
||||
# Run tests
|
||||
go test ./...
|
||||
|
||||
# Run vet
|
||||
go vet ./...
|
||||
|
||||
# Build
|
||||
go test ./... # Unit tests
|
||||
go vet ./... # Static analysis
|
||||
go build -o review-bot ./cmd/review-bot
|
||||
|
||||
# Integration tests (requires env vars)
|
||||
# Integration tests (requires env vars set)
|
||||
go test -tags=integration ./...
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
cmd/review-bot/ CLI entrypoint
|
||||
gitea/ Gitea API client
|
||||
llm/ OpenAI-compatible LLM client
|
||||
cmd/review-bot/ CLI entrypoint + orchestration
|
||||
gitea/ Gitea API client (reviews, PRs, files)
|
||||
llm/ Multi-provider LLM client (OpenAI + Anthropic)
|
||||
review/ Prompt building, response parsing, formatting
|
||||
budget/ Token estimation + context trimming
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
You are performing a security-focused code review. Your primary concern is identifying vulnerabilities, not general code quality.
|
||||
|
||||
Focus areas:
|
||||
- **Injection attacks**: SQL injection, command injection, path traversal, template injection
|
||||
- **Authentication/Authorization**: Missing auth checks, privilege escalation, IDOR
|
||||
- **Secrets exposure**: Hardcoded credentials, API keys in code, tokens in logs
|
||||
- **Input validation**: Untrusted input used without sanitization, unsafe deserialization
|
||||
- **Cryptography**: Weak algorithms, predictable randomness, improper key management
|
||||
- **Error handling**: Information leakage in error messages, stack traces exposed
|
||||
- **Dependencies**: Known vulnerable patterns, unsafe use of external libraries
|
||||
- **Race conditions**: TOCTOU bugs, unsynchronized shared state
|
||||
- **Resource exhaustion**: Unbounded allocations, missing timeouts, denial-of-service vectors
|
||||
|
||||
Rules for this review:
|
||||
- Only report findings with actual security implications. Ignore style, naming, and general code quality.
|
||||
- Severity mapping: MAJOR = exploitable vulnerability or data exposure. MINOR = defense-in-depth improvement or hardening opportunity. NIT = theoretical concern with low practical risk.
|
||||
- If the code has no security-relevant changes, APPROVE with an empty findings list.
|
||||
- Do not duplicate findings that a standard code review would catch (logic bugs, missing error checks) unless they have a security dimension.
|
||||
@@ -0,0 +1,226 @@
|
||||
// Package budget manages LLM context window budgeting for review-bot.
|
||||
//
|
||||
// It estimates token usage and progressively trims context content to fit
|
||||
// within model-specific limits. The trimming order (least important first):
|
||||
// patterns → conventions → file context → diff truncation.
|
||||
package budget
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
// modelLimit pairs a model name prefix with its context window size.
|
||||
type modelLimit struct {
|
||||
prefix string
|
||||
limit int
|
||||
}
|
||||
|
||||
// Known model context limits (in tokens), ordered longest-prefix-first
|
||||
// for deterministic matching.
|
||||
var modelLimits = []modelLimit{
|
||||
{"claude-haiku-3.5-20241022", 200_000},
|
||||
{"claude-sonnet-4-20250514", 200_000},
|
||||
{"claude-opus-4-20250514", 200_000},
|
||||
{"gpt-4.1-mini", 128_000},
|
||||
{"gpt-5-mini", 200_000},
|
||||
{"gpt-4.1", 128_000},
|
||||
{"gpt-5", 200_000},
|
||||
}
|
||||
|
||||
const defaultLimit = 128_000
|
||||
|
||||
// reserveTokens is headroom for the response generation.
|
||||
const reserveTokens = 4_000
|
||||
|
||||
const diffTruncMarker = "\n\n... [diff truncated due to context limit] ..."
|
||||
const diffTooLargeMarker = "... [diff too large for context window — review manually] ..."
|
||||
const userMetaTruncMarker = "\n... [description truncated] ..."
|
||||
|
||||
// EstimateTokens estimates the number of tokens in a string.
|
||||
// Uses the rough heuristic of ~4 bytes per token, which is
|
||||
// conservative for English text and code.
|
||||
func EstimateTokens(s string) int {
|
||||
return len(s) / 4
|
||||
}
|
||||
|
||||
// LimitForModel returns the context window size for the given model.
|
||||
// Uses longest-prefix-first matching for deterministic results.
|
||||
func LimitForModel(model string) int {
|
||||
for _, ml := range modelLimits {
|
||||
if model == ml.prefix || strings.HasPrefix(model, ml.prefix) {
|
||||
return ml.limit
|
||||
}
|
||||
}
|
||||
return defaultLimit
|
||||
}
|
||||
|
||||
// Sections holds the prompt content sections in trim priority order.
|
||||
// When the total exceeds the budget, sections are trimmed from least
|
||||
// important (Patterns) to most important (Diff).
|
||||
type Sections struct {
|
||||
SystemBase string // Core instructions (never trimmed)
|
||||
Patterns string // Language patterns (trimmed first)
|
||||
Conventions string // Repo conventions (trimmed second)
|
||||
FileContext string // Full file content (trimmed third)
|
||||
Diff string // The actual diff (trimmed last, only truncated)
|
||||
UserMeta string // PR title, description, CI status (truncated only if base exceeds budget)
|
||||
}
|
||||
|
||||
// Result holds the trimmed content and metadata about what was dropped.
|
||||
type Result struct {
|
||||
SystemPrompt string
|
||||
UserPrompt string
|
||||
Trimmed []string // Human-readable descriptions of what was trimmed
|
||||
EstTokens int // Estimated total tokens after trimming
|
||||
}
|
||||
|
||||
// Fit trims sections to fit within the model's context limit.
|
||||
// Returns the assembled prompts and a list of what was trimmed.
|
||||
func Fit(model string, sections Sections) Result {
|
||||
limit := LimitForModel(model) - reserveTokens
|
||||
|
||||
baseTokens := EstimateTokens(sections.SystemBase) + EstimateTokens(sections.UserMeta)
|
||||
available := limit - baseTokens
|
||||
if available < 0 {
|
||||
// Base content alone exceeds budget. Truncate UserMeta (keep first ~1000 tokens).
|
||||
if len(sections.UserMeta) > 4000 {
|
||||
sections.UserMeta = truncateUTF8(sections.UserMeta, 4000) + userMetaTruncMarker
|
||||
baseTokens = EstimateTokens(sections.SystemBase) + EstimateTokens(sections.UserMeta)
|
||||
available = limit - baseTokens
|
||||
}
|
||||
if available < 0 {
|
||||
available = 0
|
||||
}
|
||||
}
|
||||
|
||||
// Trimmable sections in priority order (first = dropped first)
|
||||
type entry struct {
|
||||
name string
|
||||
content *string
|
||||
}
|
||||
entries := []entry{
|
||||
{"patterns", §ions.Patterns},
|
||||
{"conventions", §ions.Conventions},
|
||||
{"file context", §ions.FileContext},
|
||||
}
|
||||
|
||||
// Check if everything fits
|
||||
totalTrimmable := EstimateTokens(sections.Diff)
|
||||
for _, e := range entries {
|
||||
totalTrimmable += EstimateTokens(*e.content)
|
||||
}
|
||||
|
||||
var trimmed []string
|
||||
if totalTrimmable > available {
|
||||
// Trim from least important
|
||||
for i := range entries {
|
||||
tokens := EstimateTokens(*entries[i].content)
|
||||
if tokens == 0 {
|
||||
continue
|
||||
}
|
||||
trimmed = append(trimmed, fmt.Sprintf("%s (~%dK tokens)", entries[i].name, tokens/1000))
|
||||
*entries[i].content = ""
|
||||
|
||||
// Recalculate
|
||||
totalTrimmable = EstimateTokens(sections.Diff)
|
||||
for _, e := range entries {
|
||||
totalTrimmable += EstimateTokens(*e.content)
|
||||
}
|
||||
if totalTrimmable <= available {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If still too large, truncate the diff
|
||||
if totalTrimmable > available {
|
||||
diffBudget := available
|
||||
for _, e := range entries {
|
||||
diffBudget -= EstimateTokens(*e.content)
|
||||
}
|
||||
if diffBudget < 0 {
|
||||
diffBudget = 0
|
||||
}
|
||||
// Reserve space for truncation marker
|
||||
markerBudget := EstimateTokens(diffTruncMarker)
|
||||
effectiveBudget := diffBudget - markerBudget
|
||||
if effectiveBudget < 0 {
|
||||
effectiveBudget = 0
|
||||
}
|
||||
maxChars := effectiveBudget * 4
|
||||
if maxChars < len(sections.Diff) {
|
||||
removed := EstimateTokens(sections.Diff) - diffBudget
|
||||
trimmed = append(trimmed, fmt.Sprintf("diff truncated (~%dK tokens removed)", removed/1000))
|
||||
if maxChars > 0 {
|
||||
if diffBudget >= markerBudget {
|
||||
sections.Diff = truncateUTF8(sections.Diff, maxChars) + diffTruncMarker
|
||||
} else {
|
||||
sections.Diff = truncateUTF8(sections.Diff, maxChars)
|
||||
}
|
||||
} else {
|
||||
sections.Diff = diffTooLargeMarker
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
finalTokens := baseTokens
|
||||
for _, e := range entries {
|
||||
finalTokens += EstimateTokens(*e.content)
|
||||
}
|
||||
finalTokens += EstimateTokens(sections.Diff)
|
||||
|
||||
return buildResult(sections, trimmed, finalTokens)
|
||||
}
|
||||
|
||||
func buildResult(s Sections, trimmed []string, estTokens int) Result {
|
||||
var sys strings.Builder
|
||||
sys.WriteString(s.SystemBase)
|
||||
if s.Patterns != "" {
|
||||
sys.WriteString("\n\n## Language Patterns & Idioms\n\nUse the following patterns as review criteria. Code that violates these established patterns is a finding:\n\n")
|
||||
sys.WriteString(s.Patterns)
|
||||
}
|
||||
if s.Conventions != "" {
|
||||
sys.WriteString("\n\n## Repository Conventions\n\nThe repository has the following coding conventions that must be respected:\n\n")
|
||||
sys.WriteString(s.Conventions)
|
||||
}
|
||||
|
||||
var usr strings.Builder
|
||||
usr.WriteString(s.UserMeta)
|
||||
if s.FileContext != "" {
|
||||
usr.WriteString("\n### Full File Context (modified files)\n\n")
|
||||
usr.WriteString(s.FileContext)
|
||||
usr.WriteString("\n")
|
||||
}
|
||||
if s.Diff != "" {
|
||||
usr.WriteString("\n### Diff (changes to review)\n\n```diff\n")
|
||||
usr.WriteString(s.Diff)
|
||||
usr.WriteString("\n```\n")
|
||||
}
|
||||
|
||||
if len(trimmed) > 0 {
|
||||
usr.WriteString("\n⚠️ Note: Context was trimmed to fit model limits. Dropped: ")
|
||||
usr.WriteString(strings.Join(trimmed, ", "))
|
||||
usr.WriteString("\n")
|
||||
}
|
||||
|
||||
return Result{
|
||||
SystemPrompt: sys.String(),
|
||||
UserPrompt: usr.String(),
|
||||
Trimmed: trimmed,
|
||||
EstTokens: estTokens,
|
||||
}
|
||||
}
|
||||
|
||||
// truncateUTF8 truncates s to at most maxBytes without splitting multi-byte
|
||||
// UTF-8 characters. Returns a valid UTF-8 string of at most maxBytes bytes.
|
||||
func truncateUTF8(s string, maxBytes int) string {
|
||||
if len(s) <= maxBytes {
|
||||
return s
|
||||
}
|
||||
for maxBytes > 0 && !utf8.RuneStart(s[maxBytes]) {
|
||||
maxBytes--
|
||||
}
|
||||
return s[:maxBytes]
|
||||
}
|
||||
@@ -0,0 +1,203 @@
|
||||
package budget
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestEstimateTokens(t *testing.T) {
|
||||
tests := []struct {
|
||||
input string
|
||||
want int
|
||||
}{
|
||||
{"", 0},
|
||||
{"abcd", 1},
|
||||
{"12345678", 2},
|
||||
{strings.Repeat("x", 400), 100},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
got := EstimateTokens(tt.input)
|
||||
if got != tt.want {
|
||||
t.Errorf("EstimateTokens(%d chars) = %d, want %d", len(tt.input), got, tt.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestLimitForModel(t *testing.T) {
|
||||
tests := []struct {
|
||||
model string
|
||||
want int
|
||||
}{
|
||||
{"gpt-4.1", 128_000},
|
||||
{"gpt-5", 200_000},
|
||||
{"gpt-5-mini", 200_000},
|
||||
{"unknown-model", defaultLimit},
|
||||
{"gpt-4.1-2026-01-01", 128_000}, // prefix match
|
||||
}
|
||||
for _, tt := range tests {
|
||||
got := LimitForModel(tt.model)
|
||||
if got != tt.want {
|
||||
t.Errorf("LimitForModel(%q) = %d, want %d", tt.model, got, tt.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_AllFits(t *testing.T) {
|
||||
s := Sections{
|
||||
SystemBase: "system instructions",
|
||||
Patterns: "some patterns",
|
||||
Conventions: "some conventions",
|
||||
FileContext: "file content",
|
||||
Diff: "diff content",
|
||||
UserMeta: "PR: title\n",
|
||||
}
|
||||
result := Fit("gpt-5", s)
|
||||
|
||||
if len(result.Trimmed) != 0 {
|
||||
t.Errorf("expected no trimming, got %v", result.Trimmed)
|
||||
}
|
||||
if !strings.Contains(result.SystemPrompt, "some patterns") {
|
||||
t.Error("expected patterns in system prompt")
|
||||
}
|
||||
if !strings.Contains(result.SystemPrompt, "some conventions") {
|
||||
t.Error("expected conventions in system prompt")
|
||||
}
|
||||
if !strings.Contains(result.UserPrompt, "file content") {
|
||||
t.Error("expected file context in user prompt")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_TrimsPatterns(t *testing.T) {
|
||||
// Create content that exceeds 128K token budget for gpt-4.1
|
||||
// Budget ≈ 128K - 4K reserve = 124K tokens = ~496K chars
|
||||
// Fill patterns with enough to push over
|
||||
bigPatterns := strings.Repeat("x", 500_000) // ~125K tokens
|
||||
s := Sections{
|
||||
SystemBase: "base",
|
||||
Patterns: bigPatterns,
|
||||
Conventions: "conventions",
|
||||
FileContext: "files",
|
||||
Diff: "diff",
|
||||
UserMeta: "meta",
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
if len(result.Trimmed) == 0 {
|
||||
t.Fatal("expected trimming")
|
||||
}
|
||||
if !strings.Contains(result.Trimmed[0], "patterns") {
|
||||
t.Errorf("expected patterns to be trimmed first, got %v", result.Trimmed)
|
||||
}
|
||||
if strings.Contains(result.SystemPrompt, bigPatterns[:100]) {
|
||||
t.Error("expected patterns to be removed from output")
|
||||
}
|
||||
// Conventions should survive
|
||||
if !strings.Contains(result.SystemPrompt, "conventions") {
|
||||
t.Error("expected conventions to survive after patterns trimmed")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_TrimsConventions(t *testing.T) {
|
||||
// Patterns + conventions + diff all exceed budget even after patterns removed
|
||||
big := strings.Repeat("y", 520_000) // ~130K tokens each (exceeds 124K budget even alone)
|
||||
s := Sections{
|
||||
SystemBase: "base",
|
||||
Patterns: big,
|
||||
Conventions: big,
|
||||
FileContext: "files",
|
||||
Diff: "diff",
|
||||
UserMeta: "meta",
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
if len(result.Trimmed) < 2 {
|
||||
t.Fatalf("expected at least 2 trimmed, got %v", result.Trimmed)
|
||||
}
|
||||
if !strings.Contains(result.Trimmed[0], "patterns") {
|
||||
t.Errorf("expected patterns trimmed first, got %s", result.Trimmed[0])
|
||||
}
|
||||
if !strings.Contains(result.Trimmed[1], "conventions") {
|
||||
t.Errorf("expected conventions trimmed second, got %s", result.Trimmed[1])
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_TruncatesDiff(t *testing.T) {
|
||||
// Only diff is huge, no patterns/conventions
|
||||
hugeDiff := strings.Repeat("z", 600_000) // ~150K tokens > 128K limit
|
||||
s := Sections{
|
||||
SystemBase: "base",
|
||||
Diff: hugeDiff,
|
||||
UserMeta: "meta",
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
if len(result.Trimmed) == 0 {
|
||||
t.Fatal("expected diff truncation")
|
||||
}
|
||||
if !strings.Contains(result.Trimmed[len(result.Trimmed)-1], "diff truncated") {
|
||||
t.Errorf("expected diff truncation note, got %v", result.Trimmed)
|
||||
}
|
||||
if !strings.Contains(result.UserPrompt, "[diff truncated due to context limit]") {
|
||||
t.Error("expected truncation marker in user prompt")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_PreservesNoteInOutput(t *testing.T) {
|
||||
big := strings.Repeat("w", 500_000)
|
||||
s := Sections{
|
||||
SystemBase: "base",
|
||||
Patterns: big,
|
||||
Diff: "small diff",
|
||||
UserMeta: "meta",
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
if !strings.Contains(result.UserPrompt, "⚠️ Note: Context was trimmed") {
|
||||
t.Error("expected trimming note in user prompt")
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
func TestFit_HugeUserMeta(t *testing.T) {
|
||||
// UserMeta so large that base alone exceeds limit
|
||||
// Use a unique marker past the truncation point
|
||||
hugeDesc := strings.Repeat("d", 5000) + "UNIQUE_MARKER_PAST_TRUNCATION" + strings.Repeat("d", 595_000)
|
||||
s := Sections{
|
||||
SystemBase: "base",
|
||||
Diff: "small diff",
|
||||
UserMeta: hugeDesc,
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
limit := LimitForModel("gpt-4.1") - reserveTokens
|
||||
if result.EstTokens > limit {
|
||||
t.Errorf("EstTokens %d exceeds limit %d", result.EstTokens, limit)
|
||||
}
|
||||
// Content past truncation point should not be present
|
||||
if strings.Contains(result.UserPrompt, "UNIQUE_MARKER_PAST_TRUNCATION") {
|
||||
t.Error("expected UserMeta to be truncated but found content past truncation point")
|
||||
}
|
||||
// Truncation marker should be present
|
||||
if !strings.Contains(result.UserPrompt, "[description truncated]") {
|
||||
t.Error("expected truncation marker in output")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFit_NeverExceedsLimit(t *testing.T) {
|
||||
// All sections huge — verify final tokens never exceed limit
|
||||
big := strings.Repeat("a", 200_000)
|
||||
s := Sections{
|
||||
SystemBase: strings.Repeat("s", 8000),
|
||||
Patterns: big,
|
||||
Conventions: big,
|
||||
FileContext: big,
|
||||
Diff: big,
|
||||
UserMeta: strings.Repeat("m", 8000),
|
||||
}
|
||||
result := Fit("gpt-4.1", s)
|
||||
|
||||
limit := LimitForModel("gpt-4.1") - reserveTokens
|
||||
if result.EstTokens > limit {
|
||||
t.Errorf("EstTokens %d exceeds limit %d (trimmed: %v)", result.EstTokens, limit, result.Trimmed)
|
||||
}
|
||||
}
|
||||
+237
-10
@@ -6,10 +6,12 @@ import (
|
||||
"fmt"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"gitea.weiker.me/rodin/review-bot/budget"
|
||||
"gitea.weiker.me/rodin/review-bot/gitea"
|
||||
"gitea.weiker.me/rodin/review-bot/llm"
|
||||
"gitea.weiker.me/rodin/review-bot/review"
|
||||
@@ -29,9 +31,11 @@ func main() {
|
||||
llmAPIKey := flag.String("llm-api-key", envOrDefault("LLM_API_KEY", ""), "LLM API key")
|
||||
llmModel := flag.String("llm-model", envOrDefault("LLM_MODEL", ""), "LLM model name")
|
||||
conventionsFile := flag.String("conventions-file", envOrDefault("CONVENTIONS_FILE", ""), "Conventions file path in repo (e.g. CLAUDE.md)")
|
||||
systemPromptFile := flag.String("system-prompt-file", envOrDefault("SYSTEM_PROMPT_FILE", ""), "Local file with additional system prompt instructions")
|
||||
patternsRepo := flag.String("patterns-repo", envOrDefault("PATTERNS_REPO", ""), "Repo with language patterns (e.g. rodin/elixir-patterns)")
|
||||
patternsFiles := flag.String("patterns-files", envOrDefault("PATTERNS_FILES", "README.md"), "Comma-separated file paths to fetch from patterns repo")
|
||||
dryRun := flag.Bool("dry-run", false, "Print review to stdout instead of posting")
|
||||
updateExisting := flag.Bool("update-existing", envOrDefaultBool("UPDATE_EXISTING", true), "Delete previous review from same bot before posting (default true)")
|
||||
llmTemp := flag.Float64("llm-temperature", envOrDefaultFloat("LLM_TEMPERATURE", 0), "LLM temperature (0 = server default)")
|
||||
llmTimeout := flag.Int("llm-timeout", envOrDefaultInt("LLM_TIMEOUT", 300), "LLM request timeout in seconds (default 300)")
|
||||
llmProvider := flag.String("llm-provider", envOrDefault("LLM_PROVIDER", "openai"), "LLM API provider: openai or anthropic")
|
||||
@@ -53,6 +57,11 @@ func main() {
|
||||
os.Exit(1)
|
||||
}
|
||||
|
||||
// Validate reviewer-name: only safe characters allowed in sentinel
|
||||
if err := validateReviewerName(*reviewerName); err != nil {
|
||||
log.Fatalf("%v", err)
|
||||
}
|
||||
|
||||
// Parse repo owner/name
|
||||
parts := strings.SplitN(*repo, "/", 2)
|
||||
if len(parts) != 2 {
|
||||
@@ -148,15 +157,62 @@ func main() {
|
||||
log.Printf("Loaded patterns from %s (%d bytes)", *patternsRepo, len(patterns))
|
||||
}
|
||||
|
||||
// Step 7: Build prompts
|
||||
systemPrompt := review.BuildSystemPrompt(conventions, patterns)
|
||||
userPrompt := review.BuildUserPrompt(pr.Title, pr.Body, diff, fileContext, ciPassed, ciDetails)
|
||||
// Step 6b: Load additional system prompt if specified
|
||||
additionalPrompt := ""
|
||||
if *systemPromptFile != "" {
|
||||
workspace := os.Getenv("GITHUB_WORKSPACE")
|
||||
if workspace == "" {
|
||||
workspace, _ = os.Getwd()
|
||||
}
|
||||
absWorkspace, err := filepath.Abs(workspace)
|
||||
if err != nil {
|
||||
log.Fatalf("Failed to resolve workspace path: %v", err)
|
||||
}
|
||||
promptPath := filepath.Join(absWorkspace, *systemPromptFile)
|
||||
promptPath = filepath.Clean(promptPath)
|
||||
if !strings.HasPrefix(promptPath, absWorkspace+string(filepath.Separator)) && promptPath != absWorkspace {
|
||||
log.Fatalf("system-prompt-file resolves outside workspace (got %q, workspace %q)", promptPath, absWorkspace)
|
||||
}
|
||||
// Resolve symlinks and re-validate to prevent symlink traversal
|
||||
resolvedPath, err := filepath.EvalSymlinks(promptPath)
|
||||
if err != nil {
|
||||
log.Fatalf("Failed to resolve system prompt file %q: %v", promptPath, err)
|
||||
}
|
||||
if !strings.HasPrefix(resolvedPath, absWorkspace+string(filepath.Separator)) && resolvedPath != absWorkspace {
|
||||
log.Fatalf("system-prompt-file symlink resolves outside workspace (got %q, workspace %q)", resolvedPath, absWorkspace)
|
||||
}
|
||||
data, err := os.ReadFile(resolvedPath)
|
||||
if err != nil {
|
||||
log.Fatalf("Failed to read system prompt file %q: %v", promptPath, err)
|
||||
}
|
||||
additionalPrompt = string(data)
|
||||
log.Printf("Loaded system prompt file: %s (%d bytes)", *systemPromptFile, len(additionalPrompt))
|
||||
}
|
||||
|
||||
// Step 7: Budget-aware prompt assembly
|
||||
systemBase := review.BuildSystemBase()
|
||||
if additionalPrompt != "" {
|
||||
systemBase += "\n\n## Additional Review Instructions\n\n" + additionalPrompt
|
||||
}
|
||||
sections := budget.Sections{
|
||||
SystemBase: systemBase,
|
||||
Patterns: patterns,
|
||||
Conventions: conventions,
|
||||
FileContext: fileContext,
|
||||
Diff: diff,
|
||||
UserMeta: review.BuildUserMeta(pr.Title, pr.Body, ciPassed, ciDetails),
|
||||
}
|
||||
budgetResult := budget.Fit(*llmModel, sections)
|
||||
log.Printf("Token estimate: ~%dK (limit: %dK)", budgetResult.EstTokens/1000, budget.LimitForModel(*llmModel)/1000)
|
||||
if len(budgetResult.Trimmed) > 0 {
|
||||
log.Printf("Context trimmed: %v", budgetResult.Trimmed)
|
||||
}
|
||||
|
||||
// Step 8: Call LLM
|
||||
log.Printf("Sending to LLM (%s)...", *llmModel)
|
||||
messages := []llm.Message{
|
||||
{Role: "system", Content: systemPrompt},
|
||||
{Role: "user", Content: userPrompt},
|
||||
{Role: "system", Content: budgetResult.SystemPrompt},
|
||||
{Role: "user", Content: budgetResult.UserPrompt},
|
||||
}
|
||||
|
||||
response, err := llmClient.Complete(ctx, messages)
|
||||
@@ -183,11 +239,112 @@ func main() {
|
||||
return
|
||||
}
|
||||
|
||||
sentinel := fmt.Sprintf("<!-- review-bot:%s -->", *reviewerName)
|
||||
|
||||
// Map findings to inline comments for lines present in the diff
|
||||
diffRanges := gitea.ParseDiffNewLines(diff)
|
||||
var inlineComments []gitea.ReviewComment
|
||||
for _, f := range result.Findings {
|
||||
if f.File != "" && f.Line > 0 && diffRanges.Contains(f.File, f.Line) {
|
||||
inlineComments = append(inlineComments, gitea.ReviewComment{
|
||||
Path: f.File,
|
||||
NewPosition: int64(f.Line),
|
||||
Body: fmt.Sprintf("**[%s]** %s", f.Severity, f.Finding),
|
||||
})
|
||||
}
|
||||
}
|
||||
if len(inlineComments) > 0 {
|
||||
log.Printf("Attaching %d inline comments", len(inlineComments))
|
||||
}
|
||||
|
||||
// --- Review update strategy ---
|
||||
// 1. No existing review → POST new
|
||||
// 2. Existing review, same state → PATCH body in place (preserves threads)
|
||||
// 3. Existing review, state change → PATCH old to "Superseded", POST new
|
||||
if *updateExisting && *reviewerName != "" {
|
||||
existingReviews, err := giteaClient.ListReviews(ctx, owner, repoName, prNumber)
|
||||
if err != nil {
|
||||
log.Printf("Warning: could not list existing reviews: %v", err)
|
||||
} else {
|
||||
// Worst-wins: escalate if a sibling blocks (need own login from existing review)
|
||||
ownLogin := ""
|
||||
existing := findOwnReview(existingReviews, sentinel)
|
||||
if existing != nil {
|
||||
ownLogin = existing.User.Login
|
||||
}
|
||||
if event == "APPROVED" && shouldEscalate(existingReviews, 0, ownLogin, sentinel) {
|
||||
log.Printf("Sibling review has REQUEST_CHANGES; escalating to REQUEST_CHANGES")
|
||||
event = "REQUEST_CHANGES"
|
||||
}
|
||||
|
||||
if existing != nil {
|
||||
if reviewUnchanged(existingReviews, reviewBody, event, sentinel) {
|
||||
log.Printf("Review unchanged from previous run; skipping to preserve threads")
|
||||
return
|
||||
}
|
||||
|
||||
// Same state → PATCH in place
|
||||
if existing.State == event {
|
||||
commentID, err := giteaClient.GetTimelineReviewCommentID(ctx, owner, repoName, prNumber, sentinel)
|
||||
if err != nil {
|
||||
log.Printf("Warning: could not find review comment ID, falling back to new post: %v", err)
|
||||
} else {
|
||||
if err := giteaClient.EditComment(ctx, owner, repoName, commentID, reviewBody); err != nil {
|
||||
log.Printf("Warning: could not edit review, falling back to new post: %v", err)
|
||||
} else {
|
||||
log.Printf("Review updated in place (comment_id=%d)", commentID)
|
||||
return
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// State change → mark old as superseded, post new below
|
||||
commentID, err := giteaClient.GetTimelineReviewCommentID(ctx, owner, repoName, prNumber, sentinel)
|
||||
if err != nil {
|
||||
log.Printf("Warning: could not find old review comment ID: %v", err)
|
||||
} else {
|
||||
supersededBody := fmt.Sprintf("~~*This review has been superseded by a newer review below.*~~\n\n%s", sentinel)
|
||||
if err := giteaClient.EditComment(ctx, owner, repoName, commentID, supersededBody); err != nil {
|
||||
log.Printf("Warning: could not mark old review as superseded: %v", err)
|
||||
} else {
|
||||
log.Printf("Marked old review as superseded (state was %s, now %s)", existing.State, event)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// POST new review (first run, or state transition fallthrough)
|
||||
log.Printf("Posting review (event=%s)...", event)
|
||||
if err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody); err != nil {
|
||||
posted, err := giteaClient.PostReview(ctx, owner, repoName, prNumber, event, reviewBody, inlineComments)
|
||||
if err != nil {
|
||||
log.Fatalf("Failed to post review: %v", err)
|
||||
}
|
||||
log.Printf("Review posted successfully!")
|
||||
log.Printf("Review posted (id=%d, user=%s)", posted.ID, posted.User.Login)
|
||||
|
||||
// Post-posting escalation: if we just posted APPROVED but a sibling
|
||||
// from the same user has REQUEST_CHANGES, mark ours as superseded and
|
||||
// re-post as REQUEST_CHANGES. This handles the first-run case where
|
||||
// we don't know our login until after posting.
|
||||
if event == "APPROVED" && *updateExisting && *reviewerName != "" {
|
||||
reviews, err := giteaClient.ListReviews(ctx, owner, repoName, prNumber)
|
||||
if err == nil && shouldEscalate(reviews, posted.ID, posted.User.Login, sentinel) {
|
||||
log.Printf("Post-posting escalation: sibling has REQUEST_CHANGES")
|
||||
// Mark our just-posted review as superseded
|
||||
commentID, err := giteaClient.GetTimelineReviewCommentID(ctx, owner, repoName, prNumber, sentinel)
|
||||
if err == nil {
|
||||
supersededBody := fmt.Sprintf("~~*This review has been superseded by a newer review below.*~~\n\n%s", sentinel)
|
||||
giteaClient.EditComment(ctx, owner, repoName, commentID, supersededBody)
|
||||
}
|
||||
// Re-post as REQUEST_CHANGES
|
||||
_, err = giteaClient.PostReview(ctx, owner, repoName, prNumber, "REQUEST_CHANGES", reviewBody, inlineComments)
|
||||
if err != nil {
|
||||
log.Printf("Warning: could not re-post as REQUEST_CHANGES: %v", err)
|
||||
} else {
|
||||
log.Printf("Review escalated to REQUEST_CHANGES")
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// fetchFileContext fetches the full content of modified files from the PR branch.
|
||||
@@ -250,12 +407,12 @@ func fetchPatterns(ctx context.Context, client *gitea.Client, patternsRepo, patt
|
||||
continue
|
||||
}
|
||||
|
||||
for filepath, content := range files {
|
||||
for filePath, content := range files {
|
||||
// Only include markdown and text files as patterns
|
||||
if !isPatternFile(filepath) {
|
||||
if !isPatternFile(filePath) {
|
||||
continue
|
||||
}
|
||||
sb.WriteString(fmt.Sprintf("### %s/%s\n\n%s\n\n", repoRef, filepath, content))
|
||||
sb.WriteString(fmt.Sprintf("### %s/%s\n\n%s\n\n", repoRef, filePath, content))
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -321,3 +478,73 @@ func envOrDefaultInt(key string, defaultVal int) int {
|
||||
}
|
||||
return defaultVal
|
||||
}
|
||||
|
||||
func envOrDefaultBool(key string, defaultVal bool) bool {
|
||||
v := strings.TrimSpace(strings.ToLower(os.Getenv(key)))
|
||||
if v == "" {
|
||||
return defaultVal
|
||||
}
|
||||
return v == "true" || v == "1" || v == "yes"
|
||||
}
|
||||
|
||||
// validateReviewerName checks that the name contains only safe characters
|
||||
// for embedding in an HTML comment sentinel ([a-zA-Z0-9_-]).
|
||||
func validateReviewerName(name string) error {
|
||||
if name == "" {
|
||||
return nil
|
||||
}
|
||||
for _, ch := range name {
|
||||
if !((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || (ch >= '0' && ch <= '9') || ch == '-' || ch == '_') {
|
||||
return fmt.Errorf("reviewer-name must contain only [a-zA-Z0-9_-] (got %q)", name)
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// shouldEscalate checks if any sibling bot review from the same user
|
||||
// (different sentinel, same token) has REQUEST_CHANGES.
|
||||
// ownLogin is the bot user login; if empty, escalation check is skipped.
|
||||
// postedID is excluded from consideration (0 means no exclusion needed).
|
||||
func shouldEscalate(reviews []gitea.Review, postedID int64, ownLogin, ownSentinel string) bool {
|
||||
if ownLogin == "" {
|
||||
return false
|
||||
}
|
||||
for _, r := range reviews {
|
||||
if r.ID == postedID || r.Stale {
|
||||
continue
|
||||
}
|
||||
// Sibling = same user, has a review-bot sentinel, but not OUR sentinel
|
||||
if r.User.Login == ownLogin && r.State == "REQUEST_CHANGES" && strings.Contains(r.Body, "<!-- review-bot:") && !strings.Contains(r.Body, ownSentinel) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// reviewUnchanged checks if an existing review with the same sentinel
|
||||
// already has identical body and state. Returns true if a re-post would
|
||||
// produce the same result (skip to preserve conversation threads).
|
||||
func reviewUnchanged(reviews []gitea.Review, newBody, newEvent, sentinel string) bool {
|
||||
for _, r := range reviews {
|
||||
if r.Stale {
|
||||
continue
|
||||
}
|
||||
if !strings.Contains(r.Body, sentinel) {
|
||||
continue
|
||||
}
|
||||
if r.State == newEvent && r.Body == newBody {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// findOwnReview locates a review matching the given sentinel in its body.
|
||||
func findOwnReview(reviews []gitea.Review, sentinel string) *gitea.Review {
|
||||
for i := range reviews {
|
||||
if strings.Contains(reviews[i].Body, sentinel) {
|
||||
return &reviews[i]
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -0,0 +1,290 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"gitea.weiker.me/rodin/review-bot/gitea"
|
||||
)
|
||||
|
||||
func TestValidateReviewerName(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
input string
|
||||
wantErr bool
|
||||
}{
|
||||
{"valid simple", "sonnet", false},
|
||||
{"valid with dash", "code-review", false},
|
||||
{"valid with underscore", "my_bot", false},
|
||||
{"valid alphanumeric", "bot123", false},
|
||||
{"valid uppercase", "MyBot", false},
|
||||
{"empty is valid", "", false},
|
||||
{"invalid html close", "foo-->", true},
|
||||
{"invalid space", "my bot", true},
|
||||
{"invalid dot", "my.bot", true},
|
||||
{"invalid slash", "my/bot", true},
|
||||
{"invalid angle", "bot<script>", true},
|
||||
{"invalid colon", "bot:name", true},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
err := validateReviewerName(tc.input)
|
||||
if tc.wantErr && err == nil {
|
||||
t.Errorf("expected error for %q, got nil", tc.input)
|
||||
}
|
||||
if !tc.wantErr && err != nil {
|
||||
t.Errorf("expected no error for %q, got %v", tc.input, err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func makeReview(id int64, login, state string, stale bool, body string) gitea.Review {
|
||||
r := gitea.Review{
|
||||
ID: id,
|
||||
Body: body,
|
||||
State: state,
|
||||
Stale: stale,
|
||||
}
|
||||
r.User.Login = login
|
||||
return r
|
||||
}
|
||||
|
||||
func TestShouldEscalate(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
reviews []gitea.Review
|
||||
postedID int64
|
||||
ownLogin string
|
||||
|
||||
ownSentinel string
|
||||
want bool
|
||||
}{
|
||||
{
|
||||
name: "no reviews",
|
||||
reviews: nil,
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "sibling same user has REQUEST_CHANGES",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "bot", "REQUEST_CHANGES", false, "bad\n<!-- review-bot:security -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "sibling different user has REQUEST_CHANGES (should NOT escalate)",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "other-bot", "REQUEST_CHANGES", false, "bad\n<!-- review-bot:gpt -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "same user REQUEST_CHANGES but stale (should NOT escalate)",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "bot", "REQUEST_CHANGES", true, "old\n<!-- review-bot:security -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "same user same sentinel (own stale review, should NOT escalate)",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "bot", "REQUEST_CHANGES", false, "old\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "same user APPROVED sibling (should NOT escalate)",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "bot", "APPROVED", false, "good\n<!-- review-bot:security -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "human REQUEST_CHANGES no sentinel (should NOT escalate)",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(101, "bot", "REQUEST_CHANGES", false, "please fix this"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "skip own posted ID",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(100, "bot", "REQUEST_CHANGES", false, "x\n<!-- review-bot:security -->"),
|
||||
},
|
||||
postedID: 100,
|
||||
ownLogin: "bot",
|
||||
ownSentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
got := shouldEscalate(tc.reviews, tc.postedID, tc.ownLogin, tc.ownSentinel)
|
||||
if got != tc.want {
|
||||
t.Errorf("shouldEscalate() = %v, want %v", got, tc.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestReviewUnchanged(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
existing []gitea.Review
|
||||
newBody string
|
||||
newEvent string
|
||||
sentinel string
|
||||
want bool
|
||||
}{
|
||||
{
|
||||
name: "no existing review",
|
||||
existing: nil,
|
||||
newBody: "new review",
|
||||
newEvent: "APPROVED",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "identical body and state",
|
||||
existing: []gitea.Review{
|
||||
makeReview(100, "bot", "APPROVED", false, "same body\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
newBody: "same body\n<!-- review-bot:sonnet -->",
|
||||
newEvent: "APPROVED",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: true,
|
||||
},
|
||||
{
|
||||
name: "same body but different state",
|
||||
existing: []gitea.Review{
|
||||
makeReview(100, "bot", "APPROVED", false, "body\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
newBody: "body\n<!-- review-bot:sonnet -->",
|
||||
newEvent: "REQUEST_CHANGES",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "different body same state",
|
||||
existing: []gitea.Review{
|
||||
makeReview(100, "bot", "APPROVED", false, "old body\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
newBody: "new body\n<!-- review-bot:sonnet -->",
|
||||
newEvent: "APPROVED",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "stale review with same body (should still post)",
|
||||
existing: []gitea.Review{
|
||||
makeReview(100, "bot", "APPROVED", true, "same\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
newBody: "same\n<!-- review-bot:sonnet -->",
|
||||
newEvent: "APPROVED",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
{
|
||||
name: "different sentinel (not our review)",
|
||||
existing: []gitea.Review{
|
||||
makeReview(100, "bot", "APPROVED", false, "body\n<!-- review-bot:gpt -->"),
|
||||
},
|
||||
newBody: "body\n<!-- review-bot:sonnet -->",
|
||||
newEvent: "APPROVED",
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
want: false,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
got := reviewUnchanged(tc.existing, tc.newBody, tc.newEvent, tc.sentinel)
|
||||
if got != tc.want {
|
||||
t.Errorf("reviewUnchanged() = %v, want %v", got, tc.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestFindOwnReview(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
reviews []gitea.Review
|
||||
sentinel string
|
||||
wantID int64
|
||||
wantNil bool
|
||||
}{
|
||||
{
|
||||
name: "no reviews",
|
||||
reviews: nil,
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
wantNil: true,
|
||||
},
|
||||
{
|
||||
name: "found by sentinel",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(42, "bot", "APPROVED", false, "review body\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
wantID: 42,
|
||||
},
|
||||
{
|
||||
name: "wrong sentinel",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(42, "bot", "APPROVED", false, "body\n<!-- review-bot:gpt -->"),
|
||||
},
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
wantNil: true,
|
||||
},
|
||||
{
|
||||
name: "multiple reviews, returns first match",
|
||||
reviews: []gitea.Review{
|
||||
makeReview(10, "bot", "APPROVED", false, "old\n<!-- review-bot:gpt -->"),
|
||||
makeReview(20, "bot", "APPROVED", false, "new\n<!-- review-bot:sonnet -->"),
|
||||
},
|
||||
sentinel: "<!-- review-bot:sonnet -->",
|
||||
wantID: 20,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
got := findOwnReview(tc.reviews, tc.sentinel)
|
||||
if tc.wantNil {
|
||||
if got != nil {
|
||||
t.Errorf("findOwnReview() = %v, want nil", got)
|
||||
}
|
||||
} else {
|
||||
if got == nil {
|
||||
t.Fatal("findOwnReview() = nil, want non-nil")
|
||||
}
|
||||
if got.ID != tc.wantID {
|
||||
t.Errorf("findOwnReview().ID = %d, want %d", got.ID, tc.wantID)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,97 @@
|
||||
# Review Update Strategy
|
||||
|
||||
review-bot uses an **edit-in-place** strategy for updating reviews. Reviews are never deleted — this preserves conversation threads on inline comments.
|
||||
|
||||
## State Transition Diagram
|
||||
|
||||
```mermaid
|
||||
stateDiagram-v2
|
||||
[*] --> NoExistingReview: First run
|
||||
|
||||
NoExistingReview --> POST_Review: Generate findings + event
|
||||
POST_Review --> PostEscalationCheck: event == APPROVED?
|
||||
|
||||
PostEscalationCheck --> Done: No sibling blocks
|
||||
PostEscalationCheck --> Supersede_And_Repost: Sibling has REQUEST_CHANGES
|
||||
Supersede_And_Repost --> Done: Posted as REQUEST_CHANGES
|
||||
|
||||
[*] --> ExistingReviewFound: Subsequent run (sentinel match)
|
||||
|
||||
ExistingReviewFound --> CheckEscalation: Determine final event
|
||||
CheckEscalation --> CompareState: Apply worst-wins if needed
|
||||
|
||||
CompareState --> SameState: existing.state == new event
|
||||
CompareState --> StateChange: existing.state != new event
|
||||
|
||||
SameState --> Skip: Body unchanged
|
||||
SameState --> PatchBody: Body changed → PATCH in place
|
||||
|
||||
StateChange --> Escalate: APPROVED → REQUEST_CHANGES
|
||||
StateChange --> Downgrade: REQUEST_CHANGES → APPROVED
|
||||
|
||||
Escalate --> Supersede: PATCH old body → "Superseded"
|
||||
Supersede --> POST_New_RC: POST new REQUEST_CHANGES
|
||||
|
||||
Downgrade --> POST_New_Approve: POST new APPROVED (old stays intact)
|
||||
|
||||
Skip --> Done
|
||||
PatchBody --> Done
|
||||
POST_New_RC --> Done
|
||||
POST_New_Approve --> Done
|
||||
```
|
||||
|
||||
## Rules
|
||||
|
||||
| Scenario | Action | Reason |
|
||||
|----------|--------|--------|
|
||||
| No existing review | POST new | First run |
|
||||
| Same state, same body | Skip | Nothing changed — preserve threads |
|
||||
| Same state, body changed | PATCH body | Update findings without losing threads |
|
||||
| APPROVED → REQUEST_CHANGES | Supersede old + POST new | Can always escalate; old APPROVED is no longer valid |
|
||||
| REQUEST_CHANGES → APPROVED | POST new APPROVED | Can't edit state; old REQUEST_CHANGES stays as historical record |
|
||||
| Sibling has REQUEST_CHANGES (worst-wins) | Escalate to REQUEST_CHANGES | PR must stay blocked if ANY reviewer blocks |
|
||||
|
||||
## Key Constraints
|
||||
|
||||
1. **Review state is immutable after POST** — Gitea has no API to change APPROVED ↔ REQUEST_CHANGES
|
||||
2. **Never delete reviews** — Deleting cascades to inline comments and reply threads
|
||||
3. **"Last review per user" wins** — Gitea uses the most recent review from a user for merge decisions
|
||||
4. **REQUEST_CHANGES reviews are never touched** — Their inline comments and threads are preserved as historical record
|
||||
5. **APPROVED reviews can be superseded** — When escalation is needed, mark old as superseded and POST new
|
||||
|
||||
## Worst-Wins (Shared Token)
|
||||
|
||||
When multiple reviewer roles share a token (e.g., `sonnet` and `security` both use `sonnet-review-bot`):
|
||||
|
||||
```
|
||||
CI Matrix Run:
|
||||
sonnet → REQUEST_CHANGES (findings)
|
||||
security → APPROVED (no security issues)
|
||||
↓
|
||||
security sees sibling REQUEST_CHANGES
|
||||
↓
|
||||
security escalates → REQUEST_CHANGES
|
||||
↓
|
||||
PR stays blocked ✓
|
||||
```
|
||||
|
||||
The **first-run case** (no existing review to read login from) uses a post-posting fallback:
|
||||
POST APPROVED → check siblings → if blocked, supersede own APPROVED → re-POST as REQUEST_CHANGES.
|
||||
|
||||
## Edit Mechanism
|
||||
|
||||
Reviews are edited via `PATCH /repos/{owner}/{repo}/issues/comments/{id}`:
|
||||
|
||||
- **Review body**: ID obtained from the timeline API (`/issues/{index}/timeline`, type `"review"`)
|
||||
- **Inline comments**: IDs obtained from `/pulls/{index}/reviews/{id}/comments`
|
||||
- **Both are editable** by the token that created them
|
||||
- **ListReviews always returns the original body** (reads from review table, not comment table) — sentinel matching works regardless of edits
|
||||
|
||||
## Inline Comments Lifecycle
|
||||
|
||||
| Event | Inline comments behavior |
|
||||
|-------|--------------------------|
|
||||
| First POST | Created on specific diff lines |
|
||||
| PATCH body (same state) | Unchanged — still current findings |
|
||||
| Supersede (state change) | Old inline comments stay (readable but on outdated code) |
|
||||
| New POST after supersede | Fresh inline comments on current diff |
|
||||
+185
-20
@@ -57,9 +57,16 @@ type ChangedFile struct {
|
||||
Status string `json:"status"`
|
||||
}
|
||||
|
||||
// ReviewComment represents an inline comment to attach to a review.
|
||||
type ReviewComment struct {
|
||||
Path string `json:"path"`
|
||||
NewPosition int64 `json:"new_position"`
|
||||
Body string `json:"body"`
|
||||
}
|
||||
|
||||
// GetPullRequest fetches PR metadata.
|
||||
func (c *Client) GetPullRequest(ctx context.Context, owner, repo string, number int) (*PullRequest, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d", c.baseURL, owner, repo, number)
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("fetch PR: %w", err)
|
||||
@@ -73,7 +80,7 @@ func (c *Client) GetPullRequest(ctx context.Context, owner, repo string, number
|
||||
|
||||
// GetPullRequestDiff fetches the unified diff for a PR.
|
||||
func (c *Client) GetPullRequestDiff(ctx context.Context, owner, repo string, number int) (string, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d.diff", c.baseURL, owner, repo, number)
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d.diff", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("fetch diff: %w", err)
|
||||
@@ -83,7 +90,7 @@ func (c *Client) GetPullRequestDiff(ctx context.Context, owner, repo string, num
|
||||
|
||||
// GetPullRequestFiles fetches the list of files changed in a PR.
|
||||
func (c *Client) GetPullRequestFiles(ctx context.Context, owner, repo string, number int) ([]ChangedFile, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/files", c.baseURL, owner, repo, number)
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/files", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("fetch PR files: %w", err)
|
||||
@@ -97,7 +104,7 @@ func (c *Client) GetPullRequestFiles(ctx context.Context, owner, repo string, nu
|
||||
|
||||
// GetCommitStatuses fetches CI statuses for a commit SHA.
|
||||
func (c *Client) GetCommitStatuses(ctx context.Context, owner, repo, sha string) ([]CommitStatus, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/commits/%s/statuses", c.baseURL, owner, repo, sha)
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/commits/%s/statuses", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), url.PathEscape(sha))
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("fetch commit statuses: %w", err)
|
||||
@@ -111,7 +118,7 @@ func (c *Client) GetCommitStatuses(ctx context.Context, owner, repo, sha string)
|
||||
|
||||
// GetFileContent fetches a file from the default branch of a repo.
|
||||
func (c *Client) GetFileContent(ctx context.Context, owner, repo, filepath string) (string, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/raw/%s", c.baseURL, owner, repo, escapePath(filepath))
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/raw/%s", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(filepath))
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("fetch file %s: %w", filepath, err)
|
||||
@@ -121,7 +128,7 @@ func (c *Client) GetFileContent(ctx context.Context, owner, repo, filepath strin
|
||||
|
||||
// GetFileContentRef fetches a file from a specific ref (branch/tag/sha) in a repo.
|
||||
func (c *Client) GetFileContentRef(ctx context.Context, owner, repo, filepath, ref string) (string, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/raw/%s?ref=%s", c.baseURL, owner, repo, escapePath(filepath), url.QueryEscape(ref))
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/raw/%s?ref=%s", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(filepath), url.QueryEscape(ref))
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("fetch file %s@%s: %w", filepath, ref, err)
|
||||
@@ -129,42 +136,54 @@ func (c *Client) GetFileContentRef(ctx context.Context, owner, repo, filepath, r
|
||||
return string(body), nil
|
||||
}
|
||||
|
||||
// PostReview submits a review to a PR.
|
||||
// PostReview submits a review to a PR and returns the created review.
|
||||
// event should be "APPROVED" or "REQUEST_CHANGES".
|
||||
func (c *Client) PostReview(ctx context.Context, owner, repo string, number int, event, body string) error {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/reviews", c.baseURL, owner, repo, number)
|
||||
// comments are optional inline comments attached to specific lines.
|
||||
func (c *Client) PostReview(ctx context.Context, owner, repo string, number int, event, body string, comments []ReviewComment) (*Review, error) {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/reviews", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), number)
|
||||
|
||||
payload := struct {
|
||||
Body string `json:"body"`
|
||||
Event string `json:"event"`
|
||||
Body string `json:"body"`
|
||||
Event string `json:"event"`
|
||||
Comments []ReviewComment `json:"comments,omitempty"`
|
||||
}{
|
||||
Body: body,
|
||||
Event: event,
|
||||
Body: body,
|
||||
Event: event,
|
||||
Comments: comments,
|
||||
}
|
||||
|
||||
data, err := json.Marshal(payload)
|
||||
if err != nil {
|
||||
return fmt.Errorf("marshal review payload: %w", err)
|
||||
return nil, fmt.Errorf("marshal review payload: %w", err)
|
||||
}
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPost, reqURL, bytes.NewReader(data))
|
||||
if err != nil {
|
||||
return fmt.Errorf("create review request: %w", err)
|
||||
return nil, fmt.Errorf("create review request: %w", err)
|
||||
}
|
||||
req.Header.Set("Authorization", "token "+c.token)
|
||||
req.Header.Set("Content-Type", "application/json")
|
||||
|
||||
resp, err := c.http.Do(req)
|
||||
if err != nil {
|
||||
return fmt.Errorf("post review: %w", err)
|
||||
return nil, fmt.Errorf("post review: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
|
||||
respBody, _ := io.ReadAll(resp.Body)
|
||||
return fmt.Errorf("post review failed (status %d): %s", resp.StatusCode, string(respBody))
|
||||
return nil, fmt.Errorf("post review failed (status %d): %s", resp.StatusCode, string(respBody))
|
||||
}
|
||||
return nil
|
||||
|
||||
respBody, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read review response: %w", err)
|
||||
}
|
||||
var review Review
|
||||
if err := json.Unmarshal(respBody, &review); err != nil {
|
||||
return nil, fmt.Errorf("parse review response: %w", err)
|
||||
}
|
||||
return &review, nil
|
||||
}
|
||||
|
||||
func (c *Client) doGet(ctx context.Context, reqURL string) ([]byte, error) {
|
||||
@@ -211,9 +230,9 @@ type ContentEntry struct {
|
||||
func (c *Client) ListContents(ctx context.Context, owner, repo, path string) ([]ContentEntry, error) {
|
||||
var reqURL string
|
||||
if path == "" {
|
||||
reqURL = fmt.Sprintf("%s/api/v1/repos/%s/%s/contents", c.baseURL, owner, repo)
|
||||
reqURL = fmt.Sprintf("%s/api/v1/repos/%s/%s/contents", c.baseURL, url.PathEscape(owner), url.PathEscape(repo))
|
||||
} else {
|
||||
reqURL = fmt.Sprintf("%s/api/v1/repos/%s/%s/contents/%s", c.baseURL, owner, repo, escapePath(path))
|
||||
reqURL = fmt.Sprintf("%s/api/v1/repos/%s/%s/contents/%s", c.baseURL, url.PathEscape(owner), url.PathEscape(repo), escapePath(path))
|
||||
}
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
@@ -266,3 +285,149 @@ func (c *Client) GetAllFilesInPath(ctx context.Context, owner, repo, path string
|
||||
}
|
||||
return results, nil
|
||||
}
|
||||
|
||||
// Review represents a pull request review from the Gitea API.
|
||||
type Review struct {
|
||||
ID int64 `json:"id"`
|
||||
Body string `json:"body"`
|
||||
User struct {
|
||||
Login string `json:"login"`
|
||||
} `json:"user"`
|
||||
State string `json:"state"`
|
||||
Stale bool `json:"stale"`
|
||||
}
|
||||
|
||||
// ListReviews returns all reviews on a pull request.
|
||||
// Paginates through all pages to ensure no reviews are missed.
|
||||
func (c *Client) ListReviews(ctx context.Context, owner, repo string, number int) ([]Review, error) {
|
||||
const pageSize = 50
|
||||
var all []Review
|
||||
for page := 1; ; page++ {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/reviews?limit=%d&page=%d",
|
||||
c.baseURL,
|
||||
url.PathEscape(owner),
|
||||
url.PathEscape(repo),
|
||||
number,
|
||||
pageSize,
|
||||
page)
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("list reviews (page %d): %w", page, err)
|
||||
}
|
||||
var batch []Review
|
||||
if err := json.Unmarshal(body, &batch); err != nil {
|
||||
return nil, fmt.Errorf("parse reviews (page %d): %w", page, err)
|
||||
}
|
||||
all = append(all, batch...)
|
||||
if len(batch) < pageSize {
|
||||
break
|
||||
}
|
||||
}
|
||||
return all, nil
|
||||
}
|
||||
|
||||
// DeleteReview deletes a review by ID. The token must belong to the review author.
|
||||
func (c *Client) DeleteReview(ctx context.Context, owner, repo string, number int, reviewID int64) error {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/pulls/%d/reviews/%d",
|
||||
c.baseURL,
|
||||
url.PathEscape(owner),
|
||||
url.PathEscape(repo),
|
||||
number,
|
||||
reviewID)
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodDelete, reqURL, nil)
|
||||
if err != nil {
|
||||
return fmt.Errorf("create delete request: %w", err)
|
||||
}
|
||||
req.Header.Set("Authorization", "token "+c.token)
|
||||
|
||||
resp, err := c.http.Do(req)
|
||||
if err != nil {
|
||||
return fmt.Errorf("delete review: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
|
||||
respBody, _ := io.ReadAll(resp.Body)
|
||||
return fmt.Errorf("delete review failed (status %d): %s", resp.StatusCode, string(respBody))
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// TimelineEvent represents an entry from the issue timeline API.
|
||||
type TimelineEvent struct {
|
||||
ID int64 `json:"id"`
|
||||
Type string `json:"type"`
|
||||
Body string `json:"body"`
|
||||
User struct {
|
||||
Login string `json:"login"`
|
||||
} `json:"user"`
|
||||
}
|
||||
|
||||
// GetTimelineReviewCommentID finds the comment ID for a review body by
|
||||
// scanning the issue timeline for a review event containing the sentinel.
|
||||
func (c *Client) GetTimelineReviewCommentID(ctx context.Context, owner, repo string, number int, sentinel string) (int64, error) {
|
||||
const pageSize = 50
|
||||
for page := 1; ; page++ {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/issues/%d/timeline?limit=%d&page=%d",
|
||||
c.baseURL,
|
||||
url.PathEscape(owner),
|
||||
url.PathEscape(repo),
|
||||
number,
|
||||
pageSize,
|
||||
page)
|
||||
body, err := c.doGet(ctx, reqURL)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("get timeline (page %d): %w", page, err)
|
||||
}
|
||||
var events []TimelineEvent
|
||||
if err := json.Unmarshal(body, &events); err != nil {
|
||||
return 0, fmt.Errorf("parse timeline (page %d): %w", page, err)
|
||||
}
|
||||
for _, ev := range events {
|
||||
if ev.Type == "review" && strings.Contains(ev.Body, sentinel) {
|
||||
return ev.ID, nil
|
||||
}
|
||||
}
|
||||
if len(events) < pageSize {
|
||||
break
|
||||
}
|
||||
}
|
||||
return 0, fmt.Errorf("no timeline event found with sentinel")
|
||||
}
|
||||
|
||||
// EditComment updates the body of an issue/review comment.
|
||||
func (c *Client) EditComment(ctx context.Context, owner, repo string, commentID int64, newBody string) error {
|
||||
reqURL := fmt.Sprintf("%s/api/v1/repos/%s/%s/issues/comments/%d",
|
||||
c.baseURL,
|
||||
url.PathEscape(owner),
|
||||
url.PathEscape(repo),
|
||||
commentID)
|
||||
|
||||
payload := struct {
|
||||
Body string `json:"body"`
|
||||
}{Body: newBody}
|
||||
data, err := json.Marshal(payload)
|
||||
if err != nil {
|
||||
return fmt.Errorf("marshal edit payload: %w", err)
|
||||
}
|
||||
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodPatch, reqURL, bytes.NewReader(data))
|
||||
if err != nil {
|
||||
return fmt.Errorf("create edit request: %w", err)
|
||||
}
|
||||
req.Header.Set("Authorization", "token "+c.token)
|
||||
req.Header.Set("Content-Type", "application/json")
|
||||
|
||||
resp, err := c.http.Do(req)
|
||||
if err != nil {
|
||||
return fmt.Errorf("edit comment: %w", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
body, _ := io.ReadAll(resp.Body)
|
||||
return fmt.Errorf("edit comment failed (status %d): %s", resp.StatusCode, body)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
+190
-3
@@ -123,15 +123,21 @@ func TestPostReview(t *testing.T) {
|
||||
}
|
||||
|
||||
w.WriteHeader(http.StatusOK)
|
||||
w.Write([]byte(`{}`))
|
||||
w.Write([]byte(`{"id":100,"user":{"login":"review-bot"},"state":"APPROVED","stale":false}`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.PostReview(context.Background(), "owner", "repo", 3, "APPROVED", "LGTM")
|
||||
review, err := client.PostReview(context.Background(), "owner", "repo", 3, "APPROVED", "LGTM", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
if review.ID != 100 {
|
||||
t.Errorf("expected review ID 100, got %d", review.ID)
|
||||
}
|
||||
if review.User.Login != "review-bot" {
|
||||
t.Errorf("expected user login %q, got %q", "review-bot", review.User.Login)
|
||||
}
|
||||
}
|
||||
|
||||
func TestGetPullRequest_Non200(t *testing.T) {
|
||||
@@ -169,7 +175,7 @@ func TestPostReview_Non200(t *testing.T) {
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "test")
|
||||
_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "test", nil)
|
||||
if err == nil {
|
||||
t.Fatal("expected error for 403, got nil")
|
||||
}
|
||||
@@ -318,3 +324,184 @@ func TestEscapePath(t *testing.T) {
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestListReviews(t *testing.T) {
|
||||
pageCount := 0
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path != "/api/v1/repos/owner/repo/pulls/5/reviews" {
|
||||
t.Errorf("unexpected path: %s", r.URL.Path)
|
||||
}
|
||||
if r.URL.Query().Get("limit") != "50" {
|
||||
t.Errorf("expected limit=50, got %s", r.URL.Query().Get("limit"))
|
||||
}
|
||||
pageCount++
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
// Return 2 results (less than page size) to signal end
|
||||
w.Write([]byte(`[{"id":10,"user":{"login":"bot-a"},"state":"APPROVED","stale":false},{"id":11,"user":{"login":"bot-b"},"state":"REQUEST_CHANGES","stale":true}]`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
reviews, err := client.ListReviews(context.Background(), "owner", "repo", 5)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
if len(reviews) != 2 {
|
||||
t.Fatalf("expected 2 reviews, got %d", len(reviews))
|
||||
}
|
||||
if reviews[0].User.Login != "bot-a" {
|
||||
t.Errorf("expected bot-a, got %s", reviews[0].User.Login)
|
||||
}
|
||||
if pageCount != 1 {
|
||||
t.Errorf("expected 1 page fetch (results < page size), got %d", pageCount)
|
||||
}
|
||||
}
|
||||
|
||||
func TestListReviews_Pagination(t *testing.T) {
|
||||
pageCount := 0
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
pageCount++
|
||||
page := r.URL.Query().Get("page")
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
if page == "1" {
|
||||
// Return exactly 50 items to trigger next page fetch
|
||||
items := "["
|
||||
for i := 0; i < 50; i++ {
|
||||
if i > 0 {
|
||||
items += ","
|
||||
}
|
||||
items += fmt.Sprintf(`{"id":%d,"user":{"login":"bot"},"state":"APPROVED","stale":false}`, i+1)
|
||||
}
|
||||
items += "]"
|
||||
w.Write([]byte(items))
|
||||
} else {
|
||||
// Page 2: return fewer than 50 to signal end
|
||||
w.Write([]byte(`[{"id":51,"user":{"login":"bot"},"state":"APPROVED","stale":false}]`))
|
||||
}
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
reviews, err := client.ListReviews(context.Background(), "owner", "repo", 5)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
if len(reviews) != 51 {
|
||||
t.Fatalf("expected 51 reviews across 2 pages, got %d", len(reviews))
|
||||
}
|
||||
if pageCount != 2 {
|
||||
t.Errorf("expected 2 page fetches, got %d", pageCount)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDeleteReview(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path != "/api/v1/repos/owner/repo/pulls/5/reviews/10" {
|
||||
t.Errorf("unexpected path: %s", r.URL.Path)
|
||||
}
|
||||
if r.Method != "DELETE" {
|
||||
t.Errorf("expected DELETE, got %s", r.Method)
|
||||
}
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.DeleteReview(context.Background(), "owner", "repo", 5, 10)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestDeleteReview_Forbidden(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.WriteHeader(http.StatusForbidden)
|
||||
w.Write([]byte(`{"message":"forbidden"}`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.DeleteReview(context.Background(), "owner", "repo", 5, 10)
|
||||
if err == nil {
|
||||
t.Fatal("expected error for 403, got nil")
|
||||
}
|
||||
}
|
||||
|
||||
func TestEditComment(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.Method != http.MethodPatch {
|
||||
t.Errorf("expected PATCH, got %s", r.Method)
|
||||
}
|
||||
if r.URL.Path != "/api/v1/repos/owner/repo/issues/comments/42" {
|
||||
t.Errorf("unexpected path: %s", r.URL.Path)
|
||||
}
|
||||
|
||||
var payload struct {
|
||||
Body string `json:"body"`
|
||||
}
|
||||
json.NewDecoder(r.Body).Decode(&payload)
|
||||
if payload.Body != "updated body" {
|
||||
t.Errorf("unexpected body: %s", payload.Body)
|
||||
}
|
||||
|
||||
w.WriteHeader(http.StatusOK)
|
||||
w.Write([]byte(`{"id": 42, "body": "updated body"}`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.EditComment(context.Background(), "owner", "repo", 42, "updated body")
|
||||
if err != nil {
|
||||
t.Fatalf("EditComment() error = %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestEditComment_Forbidden(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.WriteHeader(http.StatusForbidden)
|
||||
w.Write([]byte(`{"message": "not allowed"}`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
err := client.EditComment(context.Background(), "owner", "repo", 42, "new body")
|
||||
if err == nil {
|
||||
t.Fatal("expected error for 403 response")
|
||||
}
|
||||
}
|
||||
|
||||
func TestGetTimelineReviewCommentID(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
if r.URL.Path != "/api/v1/repos/owner/repo/issues/5/timeline" {
|
||||
t.Errorf("unexpected path: %s", r.URL.Path)
|
||||
}
|
||||
w.Write([]byte(`[
|
||||
{"id": 100, "type": "comment", "body": "random"},
|
||||
{"id": 200, "type": "review", "body": "other review <!-- review-bot:gpt -->"},
|
||||
{"id": 300, "type": "review", "body": "our review <!-- review-bot:sonnet -->"}
|
||||
]`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
id, err := client.GetTimelineReviewCommentID(context.Background(), "owner", "repo", 5, "<!-- review-bot:sonnet -->")
|
||||
if err != nil {
|
||||
t.Fatalf("GetTimelineReviewCommentID() error = %v", err)
|
||||
}
|
||||
if id != 300 {
|
||||
t.Errorf("got id=%d, want 300", id)
|
||||
}
|
||||
}
|
||||
|
||||
func TestGetTimelineReviewCommentID_NotFound(t *testing.T) {
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Write([]byte(`[{"id": 100, "type": "review", "body": "no match"}]`))
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
_, err := client.GetTimelineReviewCommentID(context.Background(), "owner", "repo", 5, "<!-- review-bot:sonnet -->")
|
||||
if err == nil {
|
||||
t.Fatal("expected error when sentinel not found")
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,85 @@
|
||||
package gitea
|
||||
|
||||
import (
|
||||
"strconv"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// DiffLineRanges maps filenames to the set of new-file line numbers present in the diff.
|
||||
type DiffLineRanges struct {
|
||||
files map[string]map[int]bool
|
||||
}
|
||||
|
||||
// Contains reports whether the given file+line is within the diff hunks.
|
||||
func (d *DiffLineRanges) Contains(file string, line int) bool {
|
||||
if d == nil || d.files == nil {
|
||||
return false
|
||||
}
|
||||
lines, ok := d.files[file]
|
||||
if !ok {
|
||||
return false
|
||||
}
|
||||
return lines[line]
|
||||
}
|
||||
|
||||
// ParseDiffNewLines parses a unified diff and extracts the new-file line numbers
|
||||
// that appear in each hunk (both added and context lines).
|
||||
func ParseDiffNewLines(diff string) *DiffLineRanges {
|
||||
result := &DiffLineRanges{files: make(map[string]map[int]bool)}
|
||||
|
||||
var currentFile string
|
||||
var newLine int
|
||||
|
||||
for _, line := range strings.Split(diff, "\n") {
|
||||
// Track current file from +++ header
|
||||
if strings.HasPrefix(line, "+++ b/") {
|
||||
currentFile = strings.TrimPrefix(line, "+++ b/")
|
||||
if result.files[currentFile] == nil {
|
||||
result.files[currentFile] = make(map[int]bool)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if strings.HasPrefix(line, "+++ /dev/null") {
|
||||
currentFile = ""
|
||||
continue
|
||||
}
|
||||
|
||||
// Parse hunk header: @@ -old,count +new,count @@ or @@ -old +new @@
|
||||
if strings.HasPrefix(line, "@@") && currentFile != "" {
|
||||
// Extract the +N part — handle both "+10,8" and "+1" forms
|
||||
parts := strings.Split(line, "+")
|
||||
if len(parts) >= 2 {
|
||||
// Take everything before comma or space
|
||||
numStr := parts[1]
|
||||
if idx := strings.IndexAny(numStr, ", "); idx != -1 {
|
||||
numStr = numStr[:idx]
|
||||
}
|
||||
n, err := strconv.Atoi(numStr)
|
||||
if err == nil {
|
||||
newLine = n
|
||||
}
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
if currentFile == "" {
|
||||
continue
|
||||
}
|
||||
|
||||
// Skip diff metadata lines
|
||||
if strings.HasPrefix(line, "\\") {
|
||||
continue
|
||||
}
|
||||
|
||||
// Count lines in hunk
|
||||
if strings.HasPrefix(line, "+") || strings.HasPrefix(line, " ") {
|
||||
result.files[currentFile][newLine] = true
|
||||
newLine++
|
||||
} else if strings.HasPrefix(line, "-") {
|
||||
// Removed lines don't advance new line counter
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
return result
|
||||
}
|
||||
@@ -0,0 +1,115 @@
|
||||
package gitea
|
||||
|
||||
import (
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestParseDiffLineRanges(t *testing.T) {
|
||||
diff := `diff --git a/main.go b/main.go
|
||||
index abc1234..def5678 100644
|
||||
--- a/main.go
|
||||
+++ b/main.go
|
||||
@@ -10,6 +10,8 @@ func main() {
|
||||
fmt.Println("hello")
|
||||
+ fmt.Println("new line 11")
|
||||
+ fmt.Println("new line 12")
|
||||
fmt.Println("existing")
|
||||
}
|
||||
@@ -30,4 +32,5 @@ func other() {
|
||||
return nil
|
||||
+ // added at line 33
|
||||
}
|
||||
diff --git a/util.go b/util.go
|
||||
new file mode 100644
|
||||
--- /dev/null
|
||||
+++ b/util.go
|
||||
@@ -0,0 +1,5 @@
|
||||
+package main
|
||||
+
|
||||
+func helper() string {
|
||||
+ return "hi"
|
||||
+}
|
||||
`
|
||||
|
||||
ranges := ParseDiffNewLines(diff)
|
||||
|
||||
// main.go should have lines 10-17 (first hunk) and 32-36 (second hunk)
|
||||
if !ranges.Contains("main.go", 11) {
|
||||
t.Error("expected main.go:11 to be in diff")
|
||||
}
|
||||
if !ranges.Contains("main.go", 12) {
|
||||
t.Error("expected main.go:12 to be in diff")
|
||||
}
|
||||
if !ranges.Contains("main.go", 10) {
|
||||
t.Error("expected main.go:10 to be in diff (context line)")
|
||||
}
|
||||
if !ranges.Contains("main.go", 33) {
|
||||
t.Error("expected main.go:33 to be in diff")
|
||||
}
|
||||
if ranges.Contains("main.go", 25) {
|
||||
t.Error("main.go:25 should NOT be in diff")
|
||||
}
|
||||
|
||||
// util.go is entirely new, lines 1-5
|
||||
if !ranges.Contains("util.go", 1) {
|
||||
t.Error("expected util.go:1 to be in diff")
|
||||
}
|
||||
if !ranges.Contains("util.go", 5) {
|
||||
t.Error("expected util.go:5 to be in diff")
|
||||
}
|
||||
if ranges.Contains("util.go", 6) {
|
||||
t.Error("util.go:6 should NOT be in diff")
|
||||
}
|
||||
|
||||
// Unknown file
|
||||
if ranges.Contains("unknown.go", 1) {
|
||||
t.Error("unknown.go should not be in diff")
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseDiffNewLines_Empty(t *testing.T) {
|
||||
ranges := ParseDiffNewLines("")
|
||||
if ranges.Contains("any.go", 1) {
|
||||
t.Error("empty diff should contain nothing")
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseDiffNewLines_NoCommaHunk(t *testing.T) {
|
||||
// Single-line hunks omit the comma: @@ -1 +1 @@
|
||||
diff := `diff --git a/single.go b/single.go
|
||||
--- a/single.go
|
||||
+++ b/single.go
|
||||
@@ -1 +1 @@
|
||||
-old line
|
||||
+new line
|
||||
`
|
||||
ranges := ParseDiffNewLines(diff)
|
||||
if !ranges.Contains("single.go", 1) {
|
||||
t.Error("expected single.go:1 to be in diff (no-comma hunk)")
|
||||
}
|
||||
if ranges.Contains("single.go", 2) {
|
||||
t.Error("single.go:2 should NOT be in diff")
|
||||
}
|
||||
}
|
||||
|
||||
func TestParseDiffNewLines_NoNewlineMarker(t *testing.T) {
|
||||
// "\ No newline at end of file" should not advance line counter
|
||||
diff := `diff --git a/noeof.go b/noeof.go
|
||||
--- a/noeof.go
|
||||
+++ b/noeof.go
|
||||
@@ -1,2 +1,2 @@
|
||||
+line one
|
||||
+line two
|
||||
\ No newline at end of file
|
||||
`
|
||||
ranges := ParseDiffNewLines(diff)
|
||||
if !ranges.Contains("noeof.go", 1) {
|
||||
t.Error("expected noeof.go:1")
|
||||
}
|
||||
if !ranges.Contains("noeof.go", 2) {
|
||||
t.Error("expected noeof.go:2")
|
||||
}
|
||||
if ranges.Contains("noeof.go", 3) {
|
||||
t.Error("noeof.go:3 should NOT be in diff (no-newline marker)")
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,88 @@
|
||||
package gitea
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestPostReview_WithComments(t *testing.T) {
|
||||
var gotPayload struct {
|
||||
Body string `json:"body"`
|
||||
Event string `json:"event"`
|
||||
Comments []struct {
|
||||
Path string `json:"path"`
|
||||
NewPosition int64 `json:"new_position"`
|
||||
Body string `json:"body"`
|
||||
} `json:"comments"`
|
||||
}
|
||||
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
json.NewDecoder(r.Body).Decode(&gotPayload)
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(200)
|
||||
json.NewEncoder(w).Encode(map[string]any{
|
||||
"id": 99,
|
||||
"body": gotPayload.Body,
|
||||
"user": map[string]any{"login": "bot"},
|
||||
})
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
comments := []ReviewComment{
|
||||
{Path: "main.go", NewPosition: 42, Body: "[MAJOR] Something bad"},
|
||||
{Path: "util.go", NewPosition: 10, Body: "[MINOR] Style issue"},
|
||||
}
|
||||
|
||||
_, err := client.PostReview(context.Background(), "owner", "repo", 1, "REQUEST_CHANGES", "summary", comments)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
|
||||
if len(gotPayload.Comments) != 2 {
|
||||
t.Fatalf("expected 2 comments, got %d", len(gotPayload.Comments))
|
||||
}
|
||||
if gotPayload.Comments[0].Path != "main.go" {
|
||||
t.Errorf("expected path main.go, got %s", gotPayload.Comments[0].Path)
|
||||
}
|
||||
if gotPayload.Comments[0].NewPosition != 42 {
|
||||
t.Errorf("expected new_position 42, got %d", gotPayload.Comments[0].NewPosition)
|
||||
}
|
||||
if gotPayload.Comments[1].Body != "[MINOR] Style issue" {
|
||||
t.Errorf("unexpected body: %s", gotPayload.Comments[1].Body)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPostReview_NilComments(t *testing.T) {
|
||||
var gotPayload map[string]any
|
||||
|
||||
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
json.NewDecoder(r.Body).Decode(&gotPayload)
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(200)
|
||||
json.NewEncoder(w).Encode(map[string]any{
|
||||
"id": 100,
|
||||
"body": "test",
|
||||
"user": map[string]any{"login": "bot"},
|
||||
})
|
||||
}))
|
||||
defer server.Close()
|
||||
|
||||
client := NewClient(server.URL, "test-token")
|
||||
_, err := client.PostReview(context.Background(), "owner", "repo", 1, "APPROVED", "all good", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
|
||||
// With nil comments, the field should be omitted (omitempty)
|
||||
comments, ok := gotPayload["comments"]
|
||||
if ok && comments != nil {
|
||||
arr, isArr := comments.([]any)
|
||||
if isArr && len(arr) > 0 {
|
||||
t.Error("expected no comments in payload when nil passed")
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -9,6 +9,11 @@ import (
|
||||
func FormatMarkdown(result *ReviewResult, reviewerName string) string {
|
||||
var sb strings.Builder
|
||||
|
||||
if reviewerName != "" {
|
||||
title := strings.ToUpper(reviewerName[:1]) + reviewerName[1:]
|
||||
sb.WriteString(fmt.Sprintf("# %s Review\n\n", title))
|
||||
}
|
||||
|
||||
sb.WriteString("## Summary\n\n")
|
||||
sb.WriteString(result.Summary)
|
||||
sb.WriteString("\n\n")
|
||||
@@ -30,6 +35,8 @@ func FormatMarkdown(result *ReviewResult, reviewerName string) string {
|
||||
|
||||
if reviewerName != "" {
|
||||
sb.WriteString(fmt.Sprintf("\n---\n*Review by %s*\n", reviewerName))
|
||||
// Hidden sentinel for identifying this bot's reviews during cleanup
|
||||
sb.WriteString(fmt.Sprintf("\n<!-- review-bot:%s -->\n", reviewerName))
|
||||
}
|
||||
|
||||
return sb.String()
|
||||
|
||||
@@ -116,3 +116,46 @@ func TestGiteaEvent(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestFormatMarkdown_Sentinel(t *testing.T) {
|
||||
result := &ReviewResult{
|
||||
Verdict: "APPROVE",
|
||||
Summary: "All good.",
|
||||
Recommendation: "Merge it.",
|
||||
}
|
||||
output := FormatMarkdown(result, "security")
|
||||
if !strings.Contains(output, "<!-- review-bot:security -->") {
|
||||
t.Error("expected sentinel comment in output")
|
||||
}
|
||||
|
||||
// Empty reviewer name should NOT have sentinel
|
||||
output2 := FormatMarkdown(result, "")
|
||||
if strings.Contains(output2, "<!-- review-bot") {
|
||||
t.Error("should not contain sentinel when reviewer name is empty")
|
||||
}
|
||||
}
|
||||
|
||||
func TestFormatMarkdown_RoleTitle(t *testing.T) {
|
||||
result := &ReviewResult{
|
||||
Verdict: "APPROVE",
|
||||
Summary: "All good.",
|
||||
Recommendation: "Merge it.",
|
||||
}
|
||||
|
||||
// With reviewer name: should have title header
|
||||
output := FormatMarkdown(result, "security")
|
||||
if !strings.Contains(output, "# Security Review\n") {
|
||||
t.Error("expected '# Security Review' header when reviewer name is set")
|
||||
}
|
||||
|
||||
output2 := FormatMarkdown(result, "gpt")
|
||||
if !strings.Contains(output2, "# Gpt Review\n") {
|
||||
t.Error("expected '# Gpt Review' header")
|
||||
}
|
||||
|
||||
// Without reviewer name: no title header
|
||||
output3 := FormatMarkdown(result, "")
|
||||
if strings.Contains(output3, "# ") && strings.Contains(output3, " Review\n") {
|
||||
t.Error("should not contain role title header when reviewer name is empty")
|
||||
}
|
||||
}
|
||||
|
||||
+26
-4
@@ -7,8 +7,10 @@ import (
|
||||
"strings"
|
||||
)
|
||||
|
||||
// BuildSystemPrompt constructs the system prompt for the LLM reviewer.
|
||||
func BuildSystemPrompt(conventions, patterns string) string {
|
||||
// BuildSystemBase returns the core system prompt instructions without
|
||||
// patterns or conventions. Used by the budget package to separate
|
||||
// trimmable from non-trimmable content.
|
||||
func BuildSystemBase() string {
|
||||
var sb strings.Builder
|
||||
|
||||
sb.WriteString("You are an expert code reviewer. Review the provided pull request diff carefully.\n\n")
|
||||
@@ -42,6 +44,15 @@ func BuildSystemPrompt(conventions, patterns string) string {
|
||||
sb.WriteString("- Line numbers should reference the new file line numbers from the diff headers.\n")
|
||||
sb.WriteString("- If the diff is empty or trivial (only formatting/whitespace), APPROVE with no findings.\n")
|
||||
|
||||
return sb.String()
|
||||
}
|
||||
|
||||
// BuildSystemPrompt constructs the full system prompt with patterns and conventions.
|
||||
// Deprecated: Use BuildSystemBase with budget.Fit for context-aware assembly.
|
||||
func BuildSystemPrompt(conventions, patterns string) string {
|
||||
var sb strings.Builder
|
||||
sb.WriteString(BuildSystemBase())
|
||||
|
||||
if patterns != "" {
|
||||
sb.WriteString(fmt.Sprintf("\n\n## Language Patterns & Idioms\n\nUse the following patterns as review criteria. Code that violates these established patterns is a finding:\n\n%s\n", patterns))
|
||||
}
|
||||
@@ -53,8 +64,9 @@ func BuildSystemPrompt(conventions, patterns string) string {
|
||||
return sb.String()
|
||||
}
|
||||
|
||||
// BuildUserPrompt constructs the user message with PR context.
|
||||
func BuildUserPrompt(title, description, diff, fileContext string, ciPassed bool, ciDetails string) string {
|
||||
// BuildUserMeta returns the PR metadata header (title, description, CI status)
|
||||
// without the diff or file context. Used by the budget package.
|
||||
func BuildUserMeta(title, description string, ciPassed bool, ciDetails string) string {
|
||||
var sb strings.Builder
|
||||
|
||||
sb.WriteString(fmt.Sprintf("## Pull Request: %s\n\n", title))
|
||||
@@ -73,6 +85,16 @@ func BuildUserPrompt(title, description, diff, fileContext string, ciPassed bool
|
||||
sb.WriteString(fmt.Sprintf("CI Details: %s\n", ciDetails))
|
||||
}
|
||||
|
||||
return sb.String()
|
||||
}
|
||||
|
||||
// BuildUserPrompt constructs the user message with PR context.
|
||||
// Deprecated: Use BuildUserMeta with budget.Fit for context-aware assembly.
|
||||
func BuildUserPrompt(title, description, diff, fileContext string, ciPassed bool, ciDetails string) string {
|
||||
var sb strings.Builder
|
||||
|
||||
sb.WriteString(BuildUserMeta(title, description, ciPassed, ciDetails))
|
||||
|
||||
if fileContext != "" {
|
||||
sb.WriteString("\n### Full File Context (modified files)\n\n")
|
||||
sb.WriteString(fileContext)
|
||||
|
||||
@@ -116,3 +116,43 @@ func TestBuildUserPrompt_WithoutFileContext(t *testing.T) {
|
||||
t.Error("should not include file context section when empty")
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
func TestBuildSystemBase(t *testing.T) {
|
||||
result := BuildSystemBase()
|
||||
if result == "" {
|
||||
t.Fatal("BuildSystemBase returned empty string")
|
||||
}
|
||||
if !strings.Contains(result, "expert code reviewer") {
|
||||
t.Error("expected reviewer role in system base")
|
||||
}
|
||||
if !strings.Contains(result, "REQUEST_CHANGES") {
|
||||
t.Error("expected verdict format in system base")
|
||||
}
|
||||
if !strings.Contains(result, "JSON") {
|
||||
t.Error("expected JSON output instruction in system base")
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildUserMeta(t *testing.T) {
|
||||
result := BuildUserMeta("Fix bug", "Some description", true, "all checks passed")
|
||||
if !strings.Contains(result, "Fix bug") {
|
||||
t.Error("expected title in user meta")
|
||||
}
|
||||
if !strings.Contains(result, "Some description") {
|
||||
t.Error("expected description in user meta")
|
||||
}
|
||||
if !strings.Contains(result, "PASSED") {
|
||||
t.Error("expected CI PASSED status")
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildUserMeta_CIFailed(t *testing.T) {
|
||||
result := BuildUserMeta("Title", "", false, "test job failed")
|
||||
if !strings.Contains(result, "FAILED") {
|
||||
t.Error("expected CI FAILED status")
|
||||
}
|
||||
if strings.Contains(result, "Description") {
|
||||
t.Error("expected no description section when empty")
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user