Compare commits

..

2 Commits

Author SHA1 Message Date
Rodin f48288bf2e fix: address review feedback — tokens, secrets, no hardcoded IPs
CI / test (pull_request) Successful in 14s
CI / review (/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 22s
CI / review (/openai/v1, gpt-4.1-mini, gpt41-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 21s
CI / review (/openai/v1, gpt-4.1, gpt41, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 22s
CI / review (/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 45s
CI / review (/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 52s
CI / review (/openai/v1, gpt-5-mini, gpt5-mini, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 48s
- Fix token_secret for gpt41/gpt5-mini/gpt41-mini: use GPT_REVIEW_TOKEN
  instead of SONNET_REVIEW_TOKEN (wrong reviewer identity)
- Move LLM base URL back to secrets.LLM_BASE_URL (prevents exfiltration
  via PR-controlled matrix values)
- Remove hardcoded internal IP from workflow file; only provider path
  suffix (/anthropic/v1, /openai/v1) remains in matrix

Addresses: security-review-bot REQUEST_CHANGES (major: exfiltration risk,
minor: HTTP/hardcoded IP) and sonnet-review-bot REQUEST_CHANGES (major:
wrong token_secret on gpt entries).
2026-05-03 08:42:08 -07:00
Rodin b4c994d0fa ci: fix reviewer models — sonnet uses Anthropic, gpt uses GPT-5
CI / test (pull_request) Successful in 14s
CI / review (http://100.86.77.84:6655/openai/v1, gpt-4.1-mini, gpt41-mini, openai, SONNET_REVIEW_TOKEN) (pull_request) Successful in 19s
CI / review (http://100.86.77.84:6655/openai/v1, gpt-4.1, gpt41, openai, SONNET_REVIEW_TOKEN) (pull_request) Successful in 22s
CI / review (http://100.86.77.84:6655/anthropic/v1, claude-sonnet-4-6, sonnet, anthropic, SONNET_REVIEW_TOKEN) (pull_request) Successful in 24s
CI / review (http://100.86.77.84:6655/openai/v1, gpt-5, gpt, openai, GPT_REVIEW_TOKEN) (pull_request) Successful in 1m14s
CI / review (http://100.86.77.84:6655/openai/v1, gpt-5, security, openai, SECURITY_REVIEW.md, SECURITY_REVIEW_TOKEN) (pull_request) Successful in 54s
CI / review (http://100.86.77.84:6655/openai/v1, gpt-5-mini, gpt5-mini, openai, SONNET_REVIEW_TOKEN) (pull_request) Successful in 55s
The matrix was wrong: "sonnet" was running GPT-5 and "gpt" was running
GPT-4.1. Now:
- sonnet → Claude Sonnet 4.6 via HAI Anthropic endpoint
- gpt → GPT-5 via HAI OpenAI endpoint
- security → GPT-5 via HAI OpenAI endpoint

Each matrix entry specifies its own provider and base_url.
2026-05-02 21:06:11 -07:00
3 changed files with 25 additions and 345 deletions
+24 -2
View File
@@ -28,12 +28,33 @@ jobs:
include:
- name: sonnet
token_secret: SONNET_REVIEW_TOKEN
model: gpt-5
provider: anthropic
llm_path: /anthropic/v1
model: claude-sonnet-4-6
- name: gpt
token_secret: GPT_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-5
- name: gpt41
token_secret: GPT_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-4.1
- name: gpt5-mini
token_secret: GPT_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-5-mini
- name: gpt41-mini
token_secret: GPT_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-4.1-mini
- name: security
token_secret: SECURITY_REVIEW_TOKEN
provider: openai
llm_path: /openai/v1
model: gpt-5
system_prompt_file: SECURITY_REVIEW.md
steps:
@@ -49,9 +70,10 @@ jobs:
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_BASE_URL: ${{ secrets.LLM_BASE_URL }}${{ matrix.llm_path }}
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_MODEL: ${{ matrix.model }}
LLM_PROVIDER: ${{ matrix.provider }}
CONVENTIONS_FILE: "CONVENTIONS.md"
PATTERNS_REPO: "rodin/go-patterns"
PATTERNS_FILES: "README.md,patterns/"
+1 -233
View File
@@ -29,12 +29,7 @@ func ParseResponse(response string) (*ReviewResult, error) {
var result ReviewResult
if err := json.Unmarshal([]byte(cleaned), &result); err != nil {
// LLMs sometimes produce JSON with unescaped quotes inside string values.
// Try to repair before giving up.
repaired := repairJSON(cleaned)
if err2 := json.Unmarshal([]byte(repaired), &result); err2 != nil {
return nil, fmt.Errorf("parse LLM response as JSON: %w\nRaw response: %s", err, response)
}
return nil, fmt.Errorf("parse LLM response as JSON: %w\nRaw response: %s", err, response)
}
// Validate verdict
@@ -79,230 +74,3 @@ func extractJSON(s string) string {
s = strings.TrimSpace(s)
return s
}
// repairJSON attempts to fix common LLM JSON issues:
// - Unescaped double quotes inside string values
//
// Strategy: walk the JSON structurally. Object keys are parsed normally (LLMs
// get those right). For string VALUES, we find all candidate closing quotes and
// pick the LAST one that leaves valid JSON structure afterward — maximizing
// string content, which is the correct bias for the "LLM put unescaped quotes
// in a string value" failure mode.
func repairJSON(s string) string {
runes := []rune(s)
var out strings.Builder
out.Grow(len(s) + 64)
i := 0
for i < len(runes) {
c := runes[i]
if c != '"' {
out.WriteRune(c)
i++
continue
}
// We hit an opening quote. Determine if this is a key or a value.
// Keys: the standard JSON parser in LLMs gets keys right, so we parse
// them normally (first unescaped quote closes).
// Values: may contain unescaped quotes — use the repair heuristic.
isValue := isValuePosition(runes, i)
if !isValue {
// Parse key/simple string normally
out.WriteRune('"')
i++
for i < len(runes) {
ch := runes[i]
if ch == '\\' && i+1 < len(runes) {
out.WriteRune(ch)
i++
out.WriteRune(runes[i])
i++
continue
}
if ch == '"' {
out.WriteRune('"')
i++
break
}
out.WriteRune(ch)
i++
}
continue
}
// Value string — find the correct close using last-valid-candidate heuristic
out.WriteRune('"')
i++
closeIdx := findClosingQuote(runes, i)
// Write everything between open and close, escaping interior quotes
for j := i; j < closeIdx; j++ {
ch := runes[j]
if ch == '\\' && j+1 < closeIdx {
// Already-escaped sequence — pass through
out.WriteRune(ch)
j++
out.WriteRune(runes[j])
} else if ch == '"' {
out.WriteRune('\\')
out.WriteRune('"')
} else {
out.WriteRune(ch)
}
}
// Write the closing quote
out.WriteRune('"')
i = closeIdx + 1
}
return out.String()
}
// isValuePosition determines if the quote at position i is opening a JSON value
// string (as opposed to an object key). We only apply repair to values that
// follow ':' since those are the free-text fields where LLMs produce unescaped
// quotes. Array elements and keys are left alone (parsed normally).
func isValuePosition(runes []rune, i int) bool {
// Look backward, skipping whitespace, for the preceding structural char
j := i - 1
for j >= 0 && (runes[j] == ' ' || runes[j] == '\t' || runes[j] == '\n' || runes[j] == '\r') {
j--
}
if j < 0 {
return false
}
// After ':' → definitely a value
return runes[j] == ':'
}
// findClosingQuote finds the index of the true closing quote for a JSON string
// value starting at position start (the character after the opening quote).
// It collects all unescaped quote candidates and returns the FIRST one that
// produces valid JSON continuation (deeper lookahead verifies the next token).
func findClosingQuote(runes []rune, start int) int {
// Collect all candidate positions for the closing quote.
var candidates []int
for j := start; j < len(runes); j++ {
if runes[j] == '\\' {
j++ // skip escaped character
continue
}
if runes[j] == '"' {
candidates = append(candidates, j)
}
}
if len(candidates) == 0 {
return len(runes)
}
if len(candidates) == 1 {
return candidates[0]
}
// Try candidates from FIRST to LAST. The correct closing quote is the
// earliest one that produces valid JSON structure after it (verified by
// deeper lookahead that checks the next token is a valid JSON start).
for _, idx := range candidates {
if isValidJSONAfterClose(runes, idx+1) {
return idx
}
}
// Fallback: return the last candidate
return candidates[len(candidates)-1]
}
// isValidJSONAfterClose checks whether the runes after a candidate closing quote
// look like valid JSON continuation for a VALUE string. Since we only use this
// for value positions, ':' is NOT a valid continuation (values are never keys).
// Checks deeper structure to avoid being fooled by JSON-like content in strings.
func isValidJSONAfterClose(runes []rune, pos int) bool {
j := pos
for j < len(runes) && (runes[j] == ' ' || runes[j] == '\t' || runes[j] == '\n' || runes[j] == '\r') {
j++
}
if j >= len(runes) {
return true
}
next := runes[j]
if next == '}' || next == ']' {
// Closing a container. Verify what follows the close is also valid:
// another structural char, comma, or EOF.
return isValidAfterContainerClose(runes, j+1)
}
if next == ',' {
// After comma, must be followed by a valid JSON token
j++
for j < len(runes) && (runes[j] == ' ' || runes[j] == '\t' || runes[j] == '\n' || runes[j] == '\r') {
j++
}
if j >= len(runes) {
return false // trailing comma with nothing after — invalid
}
return isJSONTokenStart(runes, j)
}
// ':' is NOT valid here — we're in a value position, not a key.
// Any other character is also invalid.
return false
}
// isValidAfterContainerClose checks that after a } or ], the continuation is
// structurally valid: more closes, comma+token, or EOF.
func isValidAfterContainerClose(runes []rune, pos int) bool {
j := pos
for j < len(runes) && (runes[j] == ' ' || runes[j] == '\t' || runes[j] == '\n' || runes[j] == '\r') {
j++
}
if j >= len(runes) {
return true
}
next := runes[j]
if next == '}' || next == ']' {
return isValidAfterContainerClose(runes, j+1)
}
if next == ',' {
j++
for j < len(runes) && (runes[j] == ' ' || runes[j] == '\t' || runes[j] == '\n' || runes[j] == '\r') {
j++
}
if j >= len(runes) {
return false
}
return isJSONTokenStart(runes, j)
}
return false
}
// isJSONTokenStart returns true if the rune could begin a JSON value or key.
// For keywords (true/false/null), verifies the full keyword is present.
func isJSONTokenStart(runes []rune, pos int) bool {
if pos >= len(runes) {
return false
}
r := runes[pos]
switch {
case r == '"': // string
return true
case r == '{' || r == '[': // object or array
return true
case r == 't': // true
return pos+4 <= len(runes) && string(runes[pos:pos+4]) == "true"
case r == 'f': // false
return pos+5 <= len(runes) && string(runes[pos:pos+5]) == "false"
case r == 'n': // null
return pos+4 <= len(runes) && string(runes[pos:pos+4]) == "null"
case r >= '0' && r <= '9': // number
return true
case r == '-': // negative number
return true
}
return false
}
-110
View File
@@ -1,7 +1,6 @@
package review
import (
"encoding/json"
"testing"
)
@@ -113,112 +112,3 @@ func TestParseResponse_MarkdownFencesNoLang(t *testing.T) {
t.Errorf("expected APPROVE, got %q", result.Verdict)
}
}
func TestParseResponse_UnescapedQuotesInStrings(t *testing.T) {
// Real failure from CI: Sonnet puts unescaped quotes like (e.g. "28") in findings
input := `{"verdict": "APPROVE", "summary": "Clean PR", "findings": [{"severity": "NIT", "file": "ci/Dockerfile", "line": 14, "finding": "The comment says OTP_VERSION is the major version (e.g. \"28\") but it actually contains unescaped quotes like (e.g. "28") which breaks JSON"}], "recommendation": "Ship it"}`
result, err := ParseResponse(input)
if err != nil {
t.Fatalf("expected repair to handle unescaped quotes, got error: %v", err)
}
if result.Verdict != "APPROVE" {
t.Errorf("expected APPROVE, got %q", result.Verdict)
}
if len(result.Findings) != 1 {
t.Fatalf("expected 1 finding, got %d", len(result.Findings))
}
}
func TestRepairJSON_NoOpOnValid(t *testing.T) {
valid := `{"key": "value", "num": 42}`
result := repairJSON(valid)
if result != valid {
t.Errorf("repairJSON should not modify valid JSON\n got: %s\n want: %s", result, valid)
}
}
func TestRepairJSON_FixesUnescapedQuotes(t *testing.T) {
// Interior quote followed by non-structural character
input := `{"msg": "use "foo" here"}`
result := repairJSON(input)
// Should be parseable now
var m map[string]interface{}
if err := json.Unmarshal([]byte(result), &m); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
}
func TestRepairJSON_InteriorQuoteBeforeComma(t *testing.T) {
// Bug reported by reviewer: interior quoted word immediately before a comma
input := `{"msg": "say "yes", and go"}`
result := repairJSON(input)
var m map[string]interface{}
if err := json.Unmarshal([]byte(result), &m); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
// The full string content should be preserved
msg, ok := m["msg"].(string)
if !ok {
t.Fatal("msg field missing or not a string")
}
if msg != `say "yes", and go` {
t.Errorf("unexpected msg content: %q", msg)
}
}
func TestRepairJSON_InteriorQuoteBeforeCloseBrace(t *testing.T) {
// Bug reported by reviewer: JSON-shaped syntax inside string values
input := `{"msg": "input map {"key": "val"} caused error"}`
result := repairJSON(input)
var m map[string]interface{}
if err := json.Unmarshal([]byte(result), &m); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
}
func TestRepairJSON_MultipleFields(t *testing.T) {
// Multiple string fields with unescaped quotes in different positions
input := `{"a": "hello "world"", "b": "foo"}`
result := repairJSON(input)
var m map[string]interface{}
if err := json.Unmarshal([]byte(result), &m); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
if _, ok := m["b"]; !ok {
t.Error("expected 'b' field to be preserved")
}
}
func TestRepairJSON_PreservesEscapedQuotes(t *testing.T) {
// Already-escaped quotes should not be double-escaped
input := `{"msg": "already \"escaped\" here"}`
result := repairJSON(input)
if result != input {
t.Errorf("repairJSON should not modify already-escaped quotes\n got: %s\n want: %s", result, input)
}
var m map[string]interface{}
if err := json.Unmarshal([]byte(result), &m); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
}
func TestRepairJSON_ComplexNestedContent(t *testing.T) {
// Combines both reviewer bugs: quoted words before commas AND JSON-like content
input := `{"verdict": "APPROVE", "findings": [{"finding": "The map {"key": "val"} and (e.g. "28") and say "yes", then stop"}]}`
result := repairJSON(input)
var parsed map[string]interface{}
if err := json.Unmarshal([]byte(result), &parsed); err != nil {
t.Fatalf("repaired JSON should parse, got: %v\nrepaired: %s", err, result)
}
if parsed["verdict"] != "APPROVE" {
t.Errorf("expected verdict APPROVE, got %v", parsed["verdict"])
}
}